ORCID Profile
0000-0001-5715-7154
Current Organisation
University of Technology Sydney
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Artificial Intelligence and Image Processing | Pattern Recognition and Data Mining | Information Storage, Retrieval And Management | Information Systems Development Methodologies | Pattern Recognition | Other Artificial Intelligence | Business Information Systems (Incl. Data Processing) | Library and Information Studies | Business and Management | Business Information Management (incl. Records, Knowledge and Information Management, and Intelligence) | Database Management | Simulation And Modelling | Information Systems | Computer Hardware not elsewhere classified | Database Management | Natural Language Processing | Simulation and Modelling | Computer Hardware | Decision Support And Group Support Systems |
Information processing services | Application tools and system utilities | Information Processing Services (incl. Data Entry and Capture) | Application Tools and System Utilities | Application Software Packages (excl. Computer Games) | Application packages | Computer software and services not elsewhere classified | Expanding Knowledge in the Information and Computing Sciences | Property, Business Support Services and Trade not elsewhere classified | Changing work patterns | Wholesale and Retail Trade | Expanding Knowledge in Technology | Community services not elsewhere classified | Electronic Information Storage and Retrieval Services | Mobile Data Networks and Services | Information and Communication Services not elsewhere classified | Commercial security services | Health Policy Evaluation
Publisher: Univ. Zagreb
Date: 2003
Publisher: Society for Industrial and Applied Mathematics
Date: 02-05-2013
Publisher: Univ. Zagreb
Date: 2003
Publisher: IEEE
Date: 11-2018
Publisher: Springer Berlin Heidelberg
Date: 1996
Publisher: Fuji Technology Press Ltd.
Date: 20-12-1999
Publisher: arXiv
Date: 2014
Publisher: IEEE Comput. Soc
Date: 2003
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2016
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Association for Computing Machinery (ACM)
Date: 12-2007
Abstract: Real-world data mining generally must consider and involve domain and business oriented factors such as human knowledge, constraints and business expectations. This encourages the development of a domain driven methodology to strengthen data-centered pattern mining. This report presents a review of the ACM SIGKDD Workshop on Domain Driven Data Mining (DDDM2007), held in conjunction with the Thirteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD07), which was held in San Jose, USA on 12 August, 2007. The aims and objectives of this workshop were to provide a premier forum for sharing innovative findings, knowledge, insights, experiences and lessons in tackling challenges met in domain driven, actionable knowledge discovery in the real world.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, {Graph WaveNet}, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2008
Publisher: Springer Science and Business Media LLC
Date: 05-2013
Publisher: Springer Science and Business Media LLC
Date: 11-07-2007
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11589990
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2005
DOI: 10.1109/MIS.2005.47
Publisher: IEEE Comput. Soc
Date: 2003
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2018
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2018
Publisher: Springer US
Date: 12-12-2009
Publisher: Springer US
Date: 12-12-2009
Publisher: Springer US
Date: 12-12-2009
Publisher: Springer International Publishing
Date: 2015
Publisher: IEEE
Date: 07-2018
Publisher: IEEE
Date: 2008
DOI: 10.1109/WIIAT.2008.4
Publisher: Springer International Publishing
Date: 2020
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: World Scientific Pub Co Pte Lt
Date: 06-2007
DOI: 10.1142/S0218001407005612
Abstract: Traditionally, data mining is an autonomous data-driven trial-and-error process. Its typical task is to let data tell a story disclosing hidden information, in which domain intelligence may not be necessary in targeting the demonstration of an algorithm. Often knowledge discovered is not generally interesting to business needs. Comparably, real-world applications rely on knowledge for taking effective actions. In retrospect of the evolution of KDD, this paper briefly introduces domain-driven data mining to complement traditional KDD. Domain intelligence is highlighted towards actionable knowledge discovery, which involves aspects such as domain knowledge, people, environment and evaluation. We illustrate it through mining activity patterns in social security data.
Publisher: IEEE
Date: 04-2023
Publisher: IEEE Comput. Soc
Date: 1999
Publisher: IEEE
Date: 07-2014
Publisher: Elsevier BV
Date: 06-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2015
Publisher: Elsevier BV
Date: 07-1992
Publisher: IEEE
Date: 12-2013
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: Springer Berlin Heidelberg
Date: 2004
DOI: 10.1007/B95170
Publisher: Springer Berlin Heidelberg
Date: 1999
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11610113_27
Publisher: Springer US
Date: 2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2022
Publisher: IEEE
Date: 2005
DOI: 10.1109/IAT.2005.28
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: ACM
Date: 17-10-2015
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: IEEE
Date: 07-2015
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Wiley
Date: 14-12-2007
DOI: 10.1002/9780470050118.ECSE194
Abstract: This article provides an insight for general readers on what intelligent agent is in the context of computer science and engineering. It describes the major developments that have led up to the current great interest in intelligent agents and then presents a brief discussion of the principal scientific and engineering issues in the field, which include the architecture of intelligent agents, communication languages for intelligent agents, and the methodologies and development tools for building intelligent agents. The typical applications and technological challenges for research and development over the next decade are also summarized.
Publisher: IEEE
Date: 12-2013
DOI: 10.1109/ICDM.2013.35
Publisher: Elsevier BV
Date: 06-2001
Publisher: IEEE
Date: 2004
Publisher: Elsevier BV
Date: 09-2005
Publisher: IEEE
Date: 12-2010
DOI: 10.1109/ICDMW.2010.5
Publisher: Elsevier BV
Date: 04-2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2019
Publisher: Springer Science and Business Media LLC
Date: 21-09-2016
Publisher: IEEE
Date: 12-2012
Publisher: Informa UK Limited
Date: 08-2005
Publisher: Springer Science and Business Media LLC
Date: 24-08-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2011
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer Berlin Heidelberg
Date: 2003
Publisher: Elsevier BV
Date: 09-2004
Publisher: Springer International Publishing
Date: 2014
Publisher: ACM
Date: 20-08-2006
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer Science and Business Media LLC
Date: 07-1999
DOI: 10.1007/BF02948741
Publisher: ACM Press
Date: 2015
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer International Publishing
Date: 2014
Publisher: Association for Computing Machinery (ACM)
Date: 20-07-2016
DOI: 10.1145/2910585
Abstract: Principal component analysis (PCA) has been widely applied to dimensionality reduction and data pre-processing for different applications in engineering, biology, social science, and the like. Classical PCA and its variants seek for linear projections of the original variables to obtain the low-dimensional feature representations with maximal variance. One limitation is that it is difficult to interpret the results of PCA. Besides, the classical PCA is vulnerable to certain noisy data. In this paper, we propose a Convex Sparse Principal Component Analysis (CSPCA) algorithm and apply it to feature learning. First, we show that PCA can be formulated as a low-rank regression optimization problem. Based on the discussion, the l 2, 1 -normminimization is incorporated into the objective function to make the regression coefficients sparse, thereby robust to the outliers. Also, based on the sparse model used in CSPCA, an optimal weight is assigned to each of the original feature, which in turn provides the output with good interpretability. With the output of our CSPCA, we can effectively analyze the importance of each feature under the PCA criteria. Our new objective function is convex, and we propose an iterative algorithm to optimize it. We apply the CSPCA algorithm to feature selection and conduct extensive experiments on seven benchmark datasets. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art unsupervised feature selection algorithms.
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer International Publishing
Date: 2014
Publisher: IEEE
Date: 05-2016
Publisher: Springer Science and Business Media LLC
Date: 06-04-2007
Publisher: IEEE
Date: 18-07-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2016
Publisher: IEEE
Date: 11-2007
Publisher: arXiv
Date: 2016
Publisher: Springer Berlin Heidelberg
Date: 2006
Publisher: Springer US
Date: 2009
Publisher: Elsevier BV
Date: 12-2011
Publisher: IEEE Comput. Soc
Date: 2002
Publisher: American Physical Society (APS)
Date: 10-10-2006
Publisher: IEEE
Date: 2004
Publisher: Springer Berlin Heidelberg
Date: 1998
DOI: 10.1007/BFB0095282
Publisher: Springer Berlin Heidelberg
Date: 1997
DOI: 10.1007/BFB0030089
Publisher: Springer Berlin Heidelberg
Date: 2006
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Date: 28-06-2022
Abstract: Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients' knowledge occurs in the gradient space. For ex le, clients may differ in terms of data distribution, network latency, input/output space, and/or model architecture, which can easily lead to the misalignment of their local gradients. To improve the tolerance to heterogeneity, we propose a novel federated prototype learning (FedProto) framework in which the clients and server communicate the abstract class prototypes instead of the gradients. FedProto aggregates the local prototypes collected from different clients, and then sends the global prototypes back to all clients to regularize the training of local models. The training on each client aims to minimize the classification error on the local data while keeping the resulting local prototypes sufficiently close to the corresponding global ones. Moreover, we provide a theoretical analysis to the convergence rate of FedProto under non-convex objectives. In experiments, we propose a benchmark setting tailored for heterogeneous FL, with FedProto outperforming several recent FL approaches on multiple datasets.
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11492870_5
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2016
DOI: 10.1109/MIS.2015.2
Publisher: Springer Science and Business Media LLC
Date: 19-03-2017
Publisher: Public Library of Science (PLoS)
Date: 21-02-2012
Publisher: Association for Computational Linguistics
Date: 2019
DOI: 10.18653/V1/N19-1127
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-1994
DOI: 10.1109/69.334865
Publisher: Springer Science and Business Media LLC
Date: 14-07-2017
DOI: 10.1186/S40327-017-0050-5
Abstract: The construction industry is responsible for 50% of the solid waste generated worldwide. Governments around the world formulate legislation and regulations concerning recycling and re-using building materials, aiming to reduce waste and environmental impact. Researchers have also been developing strategies and models of waste management for construction and demolition of buildings. The application of Building Information Modeling (BIM) is an ex le of this. BIM is emergent technology commonly used to maximize the efficiency of design, construction and maintenance throughout the entire lifecycle. The uses of BIM on deconstruction or demolition are not common especially the fixtures and fittings of buildings are not considered in BIM models. The development of BIM is based on two-dimensional drawings or sketches, which may not be accurately converted to 3D BIM models. In addition, previous researches mainly focused on construction waste management. There are few studies about the deconstruction waste management focusing on demolition. To fill this gap, this paper aims to develop a framework using a reconstructed 3D model with BIM, for the purpose of improving BIM accuracy and thus developing a deconstruction waste management system to improve demolition efficiency, effective recycling and cost savings. In particular, the developed as-built BIM will be used to identify and measure recyclable materials, as well as to develop a plan for the recycling process.
Publisher: IEEE
Date: 12-2008
Publisher: Springer Berlin Heidelberg
Date: 1997
DOI: 10.1007/BFB0030087
Publisher: IEEE
Date: 1999
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2017
Publisher: Association for Computing Machinery (ACM)
Date: 21-03-2017
DOI: 10.1145/2996197
Abstract: Graphs are popularly used to represent objects with shared dependency relationships. To date, all existing graph clustering algorithms consider each node as a single attribute or a set of independent attributes, without realizing that content inside each node may also have complex structures. In this article, we formulate a new networked graph clustering task where a network contains a set of inter-connected (or networked) super-nodes, each of which is a single-attribute graph. The new super-node representation is applicable to many real-world applications, such as a citation network where each node denotes a paper whose content can be described as a graph, and citation relationships between papers form a networked graph (i.e., a super-graph). Networked graph clustering aims to find similar node groups, each of which contains nodes with similar content and structure information. The main challenge is to properly calculate the similarity between super-nodes for clustering. To solve the problem, we propose to characterize node similarity by integrating structure and content information of each super-node. To measure node content similarity, we use cosine distance by considering overlapped attributes between two super-nodes. To measure structure similarity, we propose an Attributed Random Walk Kernel (ARWK) to calculate the similarity between super-nodes. Detailed node content analysis is also included to build relationships between super-nodes with shared internal structure information, so the structure similarity can be calculated in a precise way. By integrating the structure similarity and content similarity as one matrix, the spectral clustering is used to achieve networked graph clustering. Our method enjoys sound theoretical properties, including bounded similarities and better structure similarity assessment than traditional graph clustering methods. Experiments on real-world applications demonstrate that our method significantly outperforms baseline approaches.
Publisher: World Scientific Pub Co Pte Lt
Date: 08-1998
DOI: 10.1142/S021848859800032X
Abstract: The "take-them-in-or-leave-them-out" of prior probabilities is a key problem in uncertain reasonings. The EMYCIN uncertain reasoning model is inconsistent with probability theory, due to 'leaving them out', while the PROSPECTOR uncertain reasoning model is substantially consistent with probability theory, due to 'taking them in'. This presents a difficult task for human experts when supplying prior probabilities. In this paper, in order to overcome the difficulty, we propose a hybrid uncertain reasoning model, by combing rule strengths in the PROSPECTOR model with rule strengths in the EMYCIN model. Moreover, different forms of rule strength will enable human experts to supply values for the rule strengths more flexibly in a knowledge base. Finally, an ex le is given to illustrate the power of our methodology.
Publisher: Springer Science and Business Media LLC
Date: 04-11-2012
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11589990_15
Publisher: Elsevier BV
Date: 03-2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2017
Abstract: This paper addresses social network embedding, which aims to embed social network nodes, including user profile information, into a latent low-dimensional space. Most of the existing works on network embedding only consider network structure, but ignore user-generated content that could be potentially helpful in learning a better joint network representation. Different from rich node content in citation networks, user profile information in social networks is useful but noisy, sparse, and incomplete. To properly utilize this information, we propose a new algorithm called User Profile Preserving Social Network Embedding (UPP-SNE), which incorporates user profile with network structure to jointly learn a vector representation of a social network. The theme of UPP-SNE is to embed user profile information via a nonlinear mapping into a consistent subspace, where network structure is seamlessly encoded to jointly learn informative node representations. Extensive experiments on four real-world social networks show that compared to state-of-the-art baselines, our method learns better social network representations and achieves substantial performance gains in node classification and clustering tasks.
Publisher: ACM
Date: 10-08-2015
Publisher: Springer Berlin Heidelberg
Date: 2001
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2023
Abstract: Federated recommendation is a new Internet service architecture that aims to provide privacy-preserving recommendation services in federated settings. Existing solutions are used to combine distributed recommendation algorithms and privacy-preserving mechanisms. Thus it inherently takes the form of heavyweight models at the server and hinders the deployment of on-device intelligent models to end-users. This paper proposes a novel Personalized Federated Recommendation (PFedRec) framework to learn many user-specific lightweight models to be deployed on smart devices rather than a heavyweight model on a server. Moreover, we propose a new dual personalization mechanism to effectively learn fine-grained personalization on both users and items. The overall learning process is formulated into a unified federated optimization framework. Specifically, unlike previous methods that share exactly the same item embeddings across users in a federated system, dual personalization allows mild finetuning of item embeddings for each user to generate user-specific views for item representations which can be integrated into existing federated recommendation methods to gain improvements immediately. Experiments on multiple benchmark datasets have demonstrated the effectiveness of PFedRec and the dual personalization mechanism. Moreover, we provide visualizations and in-depth analysis of the personalization techniques in item embedding, which shed novel insights on the design of recommender systems in federated settings. The code is available.
Publisher: Springer Science and Business Media LLC
Date: 26-08-2019
Publisher: Springer Berlin Heidelberg
Date: 1997
DOI: 10.1007/BFB0030077
Publisher: ACM
Date: 12-08-2007
Publisher: IEEE
Date: 2002
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2017
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11546849_30
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: Springer International Publishing
Date: 2015
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2017
Abstract: Review rating prediction is an important research topic. The problem was approached from either the perspective of recommender systems (RS) or that of sentiment analysis (SA). Recent SA research using deep neural networks (DNNs) has realized the importance of user and product interaction for better interpreting the sentiment of reviews. However, the complexity of DNN models in terms of the scale of parameters is very high, and the performance is not always satisfying especially when user-product interaction is sparse. In this paper, we propose a simple, extensible RS-based model, called Text-driven Latent Factor Model (TLFM), to capture the semantics of reviews, user preferences and product characteristics by jointly optimizing two components, a user-specific LFM and a product-specific LFM, each of which decomposes text into a specific low-dimension representation. Furthermore, we address the cold-start issue by developing a novel Pairwise Rating Comparison strategy (PRC), which utilizes the difference between ratings on common user roduct as supplementary information to calibrate parameter estimation. Experiments conducted on IMDB and Yelp datasets validate the advantage of our approach over state-of-the-art baseline methods.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2010
Publisher: Informa UK Limited
Date: 06-2004
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2018
Abstract: Attributed network embedding aims to learn a low-dimensional representation for each node of a network, considering both attributes and structure information of the node. However, the learning based methods usually involve substantial cost in time, which makes them impractical without the help of a powerful workhorse. In this paper, we propose a simple yet effective algorithm, named NetHash, to solve this problem only with moderate computing capacity. NetHash employs the randomized hashing technique to encode shallow trees, each of which is rooted at a node of the network. The main idea is to efficiently encode both attributes and structure information of each node by recursively sketching the corresponding rooted tree from bottom (i.e., the predefined highest-order neighboring nodes) to top (i.e., the root node), and particularly, to preserve as much information closer to the root node as possible. Our extensive experimental results show that the proposed algorithm, which does not need learning, runs significantly faster than the state-of-the-art learning-based network embedding methods while achieving competitive or even better performance in accuracy.
Publisher: IEEE
Date: 12-2009
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11610113_6
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: Springer International Publishing
Date: 2015
Publisher: IEEE
Date: 11-2007
DOI: 10.1109/IAT.2007.16
Publisher: IGI Global
Date: 2010
DOI: 10.4018/978-1-60566-754-6.CH005
Abstract: In this chapter, the authors propose a novel framework for rare class association rule mining. In each class association rule, the right-hand is a target class while the left-hand may contain one or more attributes. This algorithm is focused on the multiple imbalanced attributes on the left-hand. In the proposed framework, the rules with and without imbalanced attributes are processed in parallel. The rules without imbalanced attributes are mined through a standard algorithm while the rules with imbalanced attributes are mined based on newly defined measurements. Through simple transformation, these measurements can be in a uniform space so that only a few parameters need to be specified by user. In the case study, the proposed algorithm is applied in the social security field. Although some attributes are severely imbalanced, rules with a minority of imbalanced attributes have been mined efficiently.
Publisher: Informa UK Limited
Date: 2006
Publisher: Springer Berlin Heidelberg
Date: 2004
Publisher: IEEE
Date: 12-2014
DOI: 10.1109/ICDM.2014.97
Publisher: Association for Computing Machinery (ACM)
Date: 18-01-2016
DOI: 10.1145/2806889
Abstract: Witnessing the wide spread of malicious information in large networks, we develop an efficient method to detect anomalous diffusion sources and thus protect networks from security and privacy attacks. To date, most existing work on diffusion sources detection are based on the assumption that network snapshots that reflect information diffusion can be obtained continuously. However, obtaining snapshots of an entire network needs to deploy detectors on all network nodes and thus is very expensive. Alternatively, in this article, we study the diffusion sources locating problem by learning from information diffusion data collected from only a small subset of network nodes. Specifically, we present a new regression learning model that can detect anomalous diffusion sources by jointly solving five challenges, that is, unknown number of source nodes, few activated detectors, unknown initial propagation time, uncertain propagation path and uncertain propagation time delay. We theoretically analyze the strength of the model and derive performance bounds. We empirically test and compare the model using both synthetic and real-world networks to demonstrate its performance.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2017
Publisher: IEEE
Date: 11-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2015
Publisher: Informa UK Limited
Date: 05-2003
DOI: 10.1080/713827180
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 1999
DOI: 10.1109/69.774105
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2016
Publisher: Elsevier BV
Date: 09-2011
Publisher: Springer Science and Business Media LLC
Date: 2005
Publisher: IEEE
Date: 11-2007
DOI: 10.1109/IAT.2007.47
Publisher: Elsevier BV
Date: 07-2012
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: International World Wide Web Conferences Steering Committee
Date: 03-04-2017
Publisher: IEEE
Date: 2008
Publisher: Informa UK Limited
Date: 05-2003
DOI: 10.1080/713827179
Publisher: Informa UK Limited
Date: 05-2003
DOI: 10.1080/713827173
Publisher: ACM
Date: 24-10-2011
Publisher: Elsevier BV
Date: 03-2016
Publisher: ACM
Date: 21-10-2023
Publisher: Association for Computing Machinery (ACM)
Date: 10-2007
Publisher: Springer Berlin Heidelberg
Date: 2001
Publisher: ACM
Date: 18-06-2014
Publisher: ACM
Date: 24-10-2016
Publisher: IEEE
Date: 11-2015
DOI: 10.1109/ICDM.2015.42
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11576235_17
Publisher: Society for Industrial and Applied Mathematics
Date: 28-04-2014
Publisher: ACM
Date: 24-10-2016
Publisher: ACM
Date: 07-07-2016
Publisher: Elsevier BV
Date: 02-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 12-2008
Publisher: Springer International Publishing
Date: 2014
Publisher: Hindawi Limited
Date: 19-07-2018
DOI: 10.1155/2018/7861860
Publisher: Informa UK Limited
Date: 2002
Publisher: Association for Computing Machinery (ACM)
Date: 07-2004
Abstract: This paper presents an efficient method for mining both positive and negative association rules in databases. The method extends traditional associations to include association rules of forms A ⇒ ¬ B , ¬ A ⇒ B , and ¬ A ⇒ ¬ B , which indicate negative associations between itemsets. With a pruning strategy and an interestingness measure, our method scales to large databases. The method has been evaluated using both synthetic and real-world databases, and our experimental results demonstrate its effectiveness and efficiency.
Publisher: World Scientific Pub Co Pte Lt
Date: 06-2008
DOI: 10.1142/S0219622008002934
Abstract: Activity data accumulated in real life, such as terrorist activities and governmental customer contacts, present special structural and semantic complexities. Activity data may lead to or be associated with significant business impacts, and result in important actions and decision making leading to business advantage. For instance, a series of terrorist activities may trigger a disaster to society, and large amounts of fraudulent activities in social security programs may result in huge government customer debt. Uncovering these activities or activity sequences can greatly evidence and/or enhance corresponding actions in business decisions. However, mining such data challenges the existing KDD research in aspects such as unbalanced data distribution and impact-targeted pattern mining. This paper investigates the characteristics and challenges of activity data, and the methodologies and tasks of activity mining based on case-study experience in the area of social security. Activity mining aims to discover high impact activity patterns in huge volumes of unbalanced activity transactions. Activity patterns identified can be used to prevent disastrous events or improve business decision making and processes. We illustrate the above issues and prospects in mining governmental customer contacts data to recover customer debt.
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer International Publishing
Date: 2014
Publisher: Informa UK Limited
Date: 08-02-2007
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer Science and Business Media LLC
Date: 11-1999
DOI: 10.1007/BF03325108
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2012
Publisher: IEEE
Date: 11-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2018
Publisher: Elsevier BV
Date: 10-2003
Publisher: IEEE
Date: 07-2010
Publisher: IGI Global
Date: 2008
DOI: 10.4018/978-1-59904-960-1.CH009
Abstract: Input selection is a crucial step for nonlinear regression modeling problem, which contributes to build an interpretable model with less computation. Most of the available methods are model-based, and few of them are model-free. Model-based methods often make use of prediction error or sensitivity analysis for input selection and Model-free methods exploit consistency. In this paper, we show the underlying relationship between sensitivity analysis and consistency analysis for input selection, and then derive an efficient model-free method from our common sense, and then formulate this common sense by fuzzy logic, thus it can be called Fuzzy Consistency Analysis (FCA). In contrast to available methods, FCA has the following desirable properties: 1) it is a model-free method so that it will not be biased on a specific model, exploiting “what the data say” rather than “what the model say”, which is the essential point of data mining – input selection should not be biased on a specific model. 2) it is implemented as efficiently as classical model-free methods, but more flexible than them. 3) it can be directly applied to a data set with mix continuous and discrete inputs without doing rotation. Four benchmark problems study indicates that the proposed method works effectively for nonlinear problems. With the input selection procedure, the underlying reasons which effect the prediction are work out, which helps to gain an insight into a specific problem and servers the purpose of data mining very well.
Publisher: IGI Global
Date: 2008
DOI: 10.4018/978-1-59904-960-1.CH008
Abstract: Quantitative intelligence based traditional data mining is facing grand challenges from real-world enterprise and cross-organization applications. For instance, the usual demonstration of specific algorithms cannot support business users to take actions to their advantage and needs. We think this is due to Quantitative Intelligence focused data-driven philosophy. It either views data mining as an autonomous data-driven, trial-and-error process, or only analyzes business issues in an isolated, case-by-case manner. Based on experience and lessons learnt from real-world data mining and complex systems, this article proposes a practical data mining methodology referred to as Domain-Driven Data Mining. On top of quantitative intelligence and hidden knowledge in data, domain-driven data mining aims to meta-synthesize quantitative intelligence and qualitative intelligence in mining complex applications in which human is in the loop. It targets actionable knowledge discovery in constrained environment for satisfying user preference. Domain-driven methodology consists of key components including understanding constrained environment, business-technical questionnaire, representing and involving domain knowledge, human-mining cooperation and interaction, constructing next-generation mining infrastructure, in-depth pattern mining and postprocessing, business interestingness and actionability enhancement, and loop-closed human-cooperated iterative refinement. Domain-driven data mining complements the data-driven methodology, the metasynthesis of qualitative intelligence and quantitative intelligence has potential to discover knowledge from complex systems, and enhance knowledge actionability for practical use by industry and business.
Publisher: Springer Berlin Heidelberg
Date: 2004
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11430919_87
Publisher: Springer Berlin Heidelberg
Date: 1999
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2018
Abstract: Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.
Publisher: IEEE
Date: 12-2014
DOI: 10.1109/ICDM.2014.55
Publisher: Informa UK Limited
Date: 05-2002
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-1995
DOI: 10.1109/26.387428
Publisher: ACM
Date: 29-10-2012
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: World Scientific Pub Co Pte Lt
Date: 08-2002
DOI: 10.1142/S0218488502001557
Abstract: This paper develops a hybrid model which provides a unified framework for the following four kinds of reasoning: 1) Zadeh's fuzzy approximate reasoning 2) truth-qualification uncertain reasoning with respect to fuzzy propositions 3) fuzzy default reasoning (proposed, in this paper, as an extension of Reiter's default reasoning) and 4) truth-qualification uncertain default reasoning associated with fuzzy statements (developed in this paper to enrich fuzzy default reasoning with uncertain information). Our hybrid model has the following characteristics: 1) basic uncertainty is estimated in terms of words or phrases in natural language and basic propositions are fuzzy 2) uncertainty, linguistically expressed, can be handled in default reasoning and 3) the four kinds of reasoning models mentioned above and their combination models will be the special cases of our hybrid model. Moreover, our model allows the reasoning to be performed in the case in which the information is fuzzy, uncertain and partial. More importantly, the problems of sharing the information among heterogeneous fuzzy, uncertain and default reasoning models can be solved efficiently by using our model. Given this, our framework can be used as a basis for information sharing and exchange in knowledge-based multi-agent systems for practical applications such as automated group negotiations. Actually, to build such a foundation is the motivation of this paper.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2023
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11539506_52
Publisher: Elsevier BV
Date: 10-2000
Publisher: Springer Science and Business Media LLC
Date: 05-1999
DOI: 10.1007/BF03325100
Publisher: Walter de Gruyter GmbH
Date: 2012
Abstract: In 2005 at the centennial anniversary of Fudan University, Shanghai, China, a new conference venue began [1]. This venue, the International Conference on Novel Materials and Synthesis (NMS) together with the International Symposium on Fine Chemistry and Functional Polymers (FCFP), is targeted to provide high-level academic exchange for both local and international chemists, materialists, physicists, engineers, and technologists in the fields of materials and synthesis. The year 2011 was the International Year of Chemistry, and it is well known that chemistry is an essential creative science for the sustainable development of humankind. As a result, the joint NMSVII/ FCFP-XXI event (www.nms-iupac.org), held in Shanghai, China, 16-21 October 2011, was more important than ever. The Conference received much support from IUPAC, The National Natural Science Foundation of China, Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials, the Science and Technology Commission of the Shanghai Municipality, and the National Basic Research Program of China (2007CB209700), and was carried out under the auspices of IUPAC. The Conference was attended by 430 participants from 40 countries and areas. The scientific program comprised 10 plenary lectures, 56 keynote lectures, 206 invited lectures, and 94 posters. Detailed, active, and lively discussions were covered by the following themes: - innovative chiral and achiral compounds - innovative bio- and biobased materials and composites - innovative polymers such as conducting, semiconducting ones, supramolecular (supermolecular, dynamers) - innovative energy systems including fuel cells, solar cells, lithium batteries, and supercapacitors - innovative nanomaterials such as 1D, 2D, and 3D nanomaterials - new ceramic materials such as superconductors, electronic, diaelectronic, ferroelectric, piezoelectric, optoelectric, and magnetic materials - new metallic materials including alloys - other novel materials including drugs, perfumes, agricultural chemicals, and photosensitive materials, displaying materials and fine ceramics and - neutron scattering and its application in fundamental and applied research on new materials. The program served to emphasize that novel materials and their preparation are dynamic research areas that are attracting growing interest from researchers, engineers, industries, and policy-makers. Furthermore, novel materials continue to find applications that serve the needs and interests of producers and consumers. A selection of 13 papers based on specially invited presentations at NMSVII/ FCFP-XXI is published in this issue to demonstrate the quality and scope of the themes of this Conference. During the Conference, the role and contributions of this high-level academic platform to novel materials and their synthesis are well realized by the participants, sponsors, and exhibitors. In addition, the organization committee established the Distinguished Award 2011 for Novel Materials and their Synthesis along with IUPAC Prof. Guoxiu Wang (Australia), Dr. Dr. Fusayoshi Masuda (Japan), Prof. Dr. André-Jean Attias (France), and Prof. Bao-Lian Su (Belgium) received the award for their excellent work. The IUPAC Prof. Jiang Novel Materials Youth Prize was awarded to two winners, Prof. Zhibo Li (China) and Dr. Jr-Hau He (Taiwan, China), for the first time. This will next be awarded in 2013. Three winners for the IUPAC Poster Prize were also awarded. Yuping Wu, Shiyou Guan, and Guoxiu Wang Conference Editors [1] Y. P. Wu. Pure Appl. Chem. 78 (10), iii (2006).
Publisher: Springer International Publishing
Date: 2016
Publisher: IEEE
Date: 2001
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Date: 03-04-2020
Abstract: The goal of zero-shot learning (ZSL) is to train a model to classify s les of classes that were not seen during training. To address this challenging task, most ZSL methods relate unseen test classes to seen(training) classes via a pre-defined set of attributes that can describe all classes in the same semantic space, so the knowledge learned on the training classes can be adapted to unseen classes. In this paper, we aim to optimize the attribute space for ZSL by training a propagation mechanism to refine the semantic attributes of each class based on its neighbors and related classes on a graph of classes. We show that the propagated attributes can produce classifiers for zero-shot classes with significantly improved performance in different ZSL settings. The graph of classes is usually free or very cheap to acquire such as WordNet or ImageNet classes. When the graph is not provided, given pre-defined semantic embeddings of the classes, we can learn a mechanism to generate the graph in an end-to-end manner along with the propagation mechanism. However, this graph-aided technique has not been well-explored in the literature. In this paper, we introduce the “attribute propagation network (APNet)”, which is composed of 1) a graph propagation model generating attribute vector for each class and 2) a parameterized nearest neighbor (NN) classifier categorizing an image to the class with the nearest attribute vector to the image's embedding. For better generalization over unseen classes, different from previous methods, we adopt a meta-learning strategy to train the propagation mechanism and the similarity metric for the NN classifier on multiple sub-graphs, each associated with a classification task over a subset of training classes. In experiments with two zero-shot learning settings and five benchmark datasets, APNet achieves either compelling performance or new state-of-the-art results.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2009
DOI: 10.1109/MIS.2009.92
Publisher: Inderscience Publishers
Date: 2007
Publisher: IEEE
Date: 12-2008
DOI: 10.1109/ICDM.2008.13
Publisher: Springer Berlin Heidelberg
Date: 2003
Publisher: Springer US
Date: 2009
Publisher: IGI Global
Date: 10-2010
Abstract: The k-nearest neighbor (kNN) imputation, as one of the most important research topics in incomplete data discovery, has been developed with great successes on industrial data. However, it is difficult to obtain a mathematical valid and simple procedure to construct confidence intervals for evaluating the imputed data. This paper studies a new estimation for missing (or incomplete) data that is a combination of the kNN imputation and bootstrap calibrated EL (Empirical Likelihood). The combination not only releases the burden of seeking a mathematical valid asymptotic theory for the kNN imputation, but also inherits the advantages of the EL method compared to the normal approximation method. Simulation results demonstrate that the bootstrap calibrated EL method performs quite well in estimating confidence intervals for the imputed data with kNN imputation method.
Publisher: Informa UK Limited
Date: 16-10-2009
Publisher: Springer US
Date: 2009
Publisher: IEEE Comput. Soc
Date: 2000
Publisher: Informa UK Limited
Date: 05-2003
DOI: 10.1080/713827171
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2010
DOI: 10.1109/TKDE.2010.74
Publisher: Elsevier BV
Date: 07-2007
Publisher: Springer Berlin Heidelberg
Date: 2004
Publisher: No publisher found
Date: 2017
Publisher: IEEE
Date: 06-2017
Publisher: IEEE
Date: 12-2008
Publisher: ACM
Date: 20-08-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 1990
DOI: 10.1109/21.57277
Publisher: Elsevier BV
Date: 03-2009
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11589990_193
Publisher: Springer Berlin Heidelberg
Date: 1996
Publisher: Springer Science and Business Media LLC
Date: 11-2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2017
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Springer Berlin Heidelberg
Date: 22-08-2005
DOI: 10.1007/11011620_7
Publisher: IEEE
Date: 2005
DOI: 10.1109/DEEC.2005.1
Publisher: Springer Science and Business Media LLC
Date: 2003
Publisher: Elsevier BV
Date: 10-2020
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: IEEE
Date: 08-2006
Publisher: Springer International Publishing
Date: 2014
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: IEEE
Date: 08-2014
Publisher: IEEE
Date: 1998
Publisher: Atlantis Press
Date: 2006
Publisher: WORLD SCIENTIFIC
Date: 04-2003
Publisher: Informa UK Limited
Date: 02-2003
DOI: 10.1080/713827103
Publisher: Springer Berlin Heidelberg
Date: 2004
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 1999
DOI: 10.1109/69.761668
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2020
Publisher: Springer Science and Business Media LLC
Date: 04-08-2010
Publisher: ACM Press
Date: 2002
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2022
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: Springer Berlin Heidelberg
Date: 1996
Publisher: Elsevier BV
Date: 05-1991
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2014
Publisher: Springer International Publishing
Date: 2016
Publisher: Association for Computing Machinery (ACM)
Date: 04-2015
DOI: 10.1145/2663356
Abstract: This article proposes LA-LDA, a location-aware probabilistic generative model that exploits location-based ratings to model user profiles and produce recommendations. Most of the existing recommendation models do not consider the spatial information of users or items however, LA-LDA supports three classes of location-based ratings, namely spatial user ratings for nonspatial items, nonspatial user ratings for spatial items, and spatial user ratings for spatial items. LA-LDA consists of two components, ULA-LDA and ILA-LDA, which are designed to take into account user and item location information, respectively. The component ULA-LDA explicitly incorporates and quantifies the influence from local public preferences to produce recommendations by considering user home locations, whereas the component ILA-LDA recommends items that are closer in both taste and travel distance to the querying users by capturing item co-occurrence patterns, as well as item location co-occurrence patterns. The two components of LA-LDA can be applied either separately or collectively, depending on the available types of location-based ratings. To demonstrate the applicability and flexibility of the LA-LDA model, we deploy it to both top- k recommendation and cold start recommendation scenarios. Experimental evidence on large-scale real-world data, including the data from Gowalla (a location-based social network), DoubanEvent (an event-based social network), and MovieLens (a movie recommendation system), reveal that LA-LDA models user profiles more accurately by outperforming existing recommendation models for top- k recommendation and the cold start problem.
Publisher: Springer Berlin Heidelberg
Date: 2003
Publisher: ACM
Date: 18-03-2013
Publisher: Springer Berlin Heidelberg
Date: 2013
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: Elsevier BV
Date: 02-2022
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Springer Berlin Heidelberg
Date: 1998
DOI: 10.1007/BFB0055026
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: IEEE
Date: 08-2012
Publisher: Springer Science and Business Media LLC
Date: 19-07-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2005
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: Springer Science and Business Media LLC
Date: 14-04-2012
Publisher: IEEE Comput. Soc
Date: 2000
Publisher: Royal Society of Chemistry (RSC)
Date: 2015
DOI: 10.1039/C5RA08987E
Abstract: The feasibility of preparing activated carbon from carbohydrates (glucose, sucrose and starch) with H 3 PO 4 activation was evaluated by comparing its physicochemical properties and Ni( ii ) adsorption ability with a reference Phragmites australis -based activated carbon.
Publisher: Springer Berlin Heidelberg
Date: 2003
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2007
DOI: 10.1109/MIS.2007.67
Publisher: Springer Berlin Heidelberg
Date: 1999
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2002
Publisher: IEEE
Date: 12-2010
DOI: 10.1109/ICDM.2010.4
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2020
Abstract: Many algorithms for Knowledge-Based Question Answering (KBQA) depend on semantic parsing, which translates a question to its logical form. When only weak supervision is provided, it is usually necessary to search valid logical forms for model training. However, a complex question typically involves a huge search space, which creates two main problems: 1) the solutions limited by computation time and memory usually reduce the success rate of the search, and 2) spurious logical forms in the search results degrade the quality of training data. These two problems lead to a poorly-trained semantic parsing model. In this work, we propose an effective search method for weakly supervised KBQA based on operator prediction for questions. With search space constrained by predicted operators, sufficient search paths can be explored, more valid logical forms can be derived, and operators possibly causing spurious logical forms can be avoided. As a result, a larger proportion of questions in a weakly supervised training set are equipped with logical forms, and fewer spurious logical forms are generated. Such high-quality training data directly contributes to a better semantic parsing model. Experimental results on one of the largest KBQA datasets (i.e., CSQA) verify the effectiveness of our approach and deliver a new state-of-the-art performance.
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11731139_96
Publisher: IEEE
Date: 2006
Publisher: IGI Global
Date: 10-2006
Abstract: Extant data mining is based on data-driven methodologies. It either views data mining as an autonomous data-driven, trial-and-error process or only analyzes business issues in an isolated, case-by-case manner. As a result, very often the knowledge discovered generally is not interesting to real business needs. Therefore, this article proposes a practical data mining methodology referred to as domain-driven data mining, which targets actionable knowledge discovery in a constrained environment for satisfying user preference. The domain-driven data mining consists of a DDID-PD framework that considers key components such as constraint-based context, integrating domain knowledge, human-machine cooperation, in-depth mining, actionability enhancement, and iterative refinement process. We also illustrate some ex les in mining actionable correlations in Australian Stock Exchange, which show that domain-driven data mining has potential to improve further the actionability of patterns for practical use by industry and business.
Publisher: Society for Industrial and Applied Mathematics
Date: 28-04-2011
Publisher: Society for Industrial and Applied Mathematics
Date: 02-05-2013
Publisher: Springer Berlin Heidelberg
Date: 2013
Publisher: IEEE
Date: 2004
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototype propagation network (PPN) trained on few-shot tasks together with data annotated by coarse-label. Given a category graph of the targeted fine-classes and some weakly-labeled coarse-classes, PPN learns an attention mechanism which propagates the prototype of one class to another on the graph, so that the K-nearest neighbor (KNN) classifier defined on the propagated prototypes results in high accuracy across different few-shot tasks. The training tasks are generated by subgraph s ling, and the training objective is obtained by accumulating the level-wise classification loss on the subgraph. On two benchmarks, PPN significantly outperforms most recent few-shot learning methods in different settings, even when they are also allowed to train on weakly-labeled data.
Publisher: Elsevier BV
Date: 08-2004
Publisher: Springer International Publishing
Date: 2016
Publisher: Springer Berlin Heidelberg
Date: 1998
DOI: 10.1007/BFB0055030
Publisher: Springer Berlin Heidelberg
Date: 1999
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2002
Publisher: ACM
Date: 14-08-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2015
Publisher: IEEE
Date: 1997
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2014
Publisher: IEEE
Date: 12-2006
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: IEEE
Date: 04-2013
Publisher: IEEE
Date: 08-2020
Publisher: Elsevier BV
Date: 04-2023
Publisher: Elsevier BV
Date: 03-2005
Publisher: World Scientific Pub Co Pte Lt
Date: 08-2004
DOI: 10.1142/S0218194004001695
Abstract: Identifying software component association is useful for component management and component retrieval. In this paper we design an evolutionary strategy to understand software structure better and identify software component association, by using genetic algorithm. Our mining strategy is effective for global search, especially when the searched space is so large that it is hardly possible to use deterministic search method.
Publisher: Springer Berlin Heidelberg
Date: 2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 08-2019
Abstract: Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step frameworks are difficult to manipulate and usually lead to suboptimal performance, mainly because the graph embedding is not goal-directed, i.e., designed for the specific clustering task. In this paper, we propose a goal-directed deep learning approach, Deep Attentional Embedded Graph Clustering (DAEGC for short). Our method focuses on attributed graphs to sufficiently explore the two sides of information in graphs. By employing an attention network to capture the importance of the neighboring nodes to a target node, our DAEGC algorithm encodes the topological structure and node content in a graph to a compact representation, on which an inner product decoder is trained to reconstruct the graph structure. Furthermore, soft labels from the graph embedding itself are generated to supervise a self-training graph clustering process, which iteratively refines the clustering results. The self-training process is jointly learned and optimized with the graph embedding in a unified framework, to mutually benefit both components. Experimental results compared with state-of-the-art algorithms demonstrate the superiority of our method.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Elsevier BV
Date: 11-2015
Publisher: ACM
Date: 03-11-2014
Publisher: Springer Berlin Heidelberg
Date: 2003
Publisher: IEEE Comput. Soc. Press
Date: 1996
Publisher: Elsevier BV
Date: 09-2011
Publisher: IEEE
Date: 11-2021
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2018
Abstract: Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two tokens, but they are not effective and efficient when applied to long sentences. By contrast, hard attention mechanisms directly select a subset of tokens but are difficult and inefficient to train due to their combinatorial nature. In this paper, we integrate both soft and hard attention into one context fusion model, "reinforced self-attention (ReSA)", for the mutual benefit of each other. In ReSA, a hard attention trims a sequence for a soft self-attention to process, while the soft attention feeds reward signals back to facilitate the training of the hard one. For this purpose, we develop a novel hard attention called "reinforced sequence s ling (RSS)", selecting tokens in parallel and trained via policy gradient. Using two RSS modules, ReSA efficiently extracts the sparse dependencies between each pair of selected tokens. We finally propose an RNN/CNN-free sentence-encoding model, "reinforced self-attention network (ReSAN)", solely based on ReSA. It achieves state-of-the-art performance on both the Stanford Natural Language Inference (SNLI) and the Sentences Involving Compositional Knowledge (SICK) datasets.
Publisher: IEEE
Date: 12-2009
DOI: 10.1109/ICDM.2009.70
Publisher: Springer Berlin Heidelberg
Date: 2002
Publisher: Springer Berlin Heidelberg
Date: 2006
Publisher: Atlantis Press
Date: 2007
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: Springer International Publishing
Date: 2016
Publisher: IEEE Comput. Soc
Date: 2003
Publisher: Springer Science and Business Media LLC
Date: 18-01-2007
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: ACM
Date: 29-06-2009
Publisher: IEEE
Date: 2004
Publisher: Association for Computing Machinery (ACM)
Date: 08-05-2021
DOI: 10.1145/3436892
Abstract: Traditional network embedding primarily focuses on learning a continuous vector representation for each node, preserving network structure and/or node content information, such that off-the-shelf machine learning algorithms can be easily applied to the vector-format node representations for network analysis. However, the learned continuous vector representations are inefficient for large-scale similarity search, which often involves finding nearest neighbors measured by distance or similarity in a continuous vector space. In this article, we propose a search efficient binary network embedding algorithm called BinaryNE to learn a binary code for each node, by simultaneously modeling node context relations and node attribute relations through a three-layer neural network. BinaryNE learns binary node representations using a stochastic gradient descent-based online learning algorithm. The learned binary encoding not only reduces memory usage to represent each node, but also allows fast bit-wise comparisons to support faster node similarity search than using Euclidean or other distance measures. Extensive experiments and comparisons demonstrate that BinaryNE not only delivers more than 25 times faster search speed, but also provides comparable or better search quality than traditional continuous vector based network embedding methods. The binary codes learned by BinaryNE also render competitive performance on node classification and node clustering tasks. The source code of the BinaryNE algorithm is available at aokunzhang/BinaryNE.
Publisher: Springer Berlin Heidelberg
Date: 2003
Publisher: ACM
Date: 11-08-2013
Publisher: Elsevier BV
Date: 04-2015
DOI: 10.1016/J.MBS.2015.01.010
Abstract: Protein kinases have been implicated in a number of diseases, where kinases participate many aspects that control cell growth, movement and death. The deregulated kinase activities and the knowledge of these disorders are of great clinical interest of drug discovery. The most critical issue is the development of safe and efficient disease diagnosis and treatment for less cost and in less time. It is critical to develop innovative approaches that aim at the root cause of a disease, not just its symptoms. Bioinformatics including genetic, genomic, mathematics and computational technologies, has become the most promising option for effective drug discovery, and has showed its potential in early stage of drug-target identification and target validation. It is essential that these aspects are understood and integrated into new methods used in drug discovery for diseases arisen from deregulated kinase activity. This article reviews bioinformatics techniques for protein kinase data management and analysis, kinase pathways and drug targets and describes their potential application in pharma ceutical industry.
Publisher: Springer Berlin Heidelberg
Date: 2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2019
Publisher: Springer Berlin Heidelberg
Date: 2000
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2008
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11731139_58
Publisher: IEEE
Date: 2005
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11527503_3
Publisher: Inderscience Publishers
Date: 2005
Publisher: IEEE
Date: 12-2016
Publisher: Elsevier BV
Date: 11-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Springer International Publishing
Date: 2021
Publisher: Springer Berlin Heidelberg
Date: 2003
Publisher: Association for Computational Linguistics
Date: 2022
Publisher: IEEE
Date: 1998
Publisher: IEEE
Date: 12-2006
DOI: 10.1109/AIDM.2006.12
Publisher: IEEE
Date: 07-2014
Publisher: IEEE
Date: 04-2001
Publisher: Springer US
Date: 12-12-2009
Publisher: WORLD SCIENTIFIC
Date: 03-10-2017
Publisher: Springer US
Date: 12-12-2009
Publisher: Springer US
Date: 12-12-2009
Publisher: Springer US
Date: 12-12-2009
Publisher: World Scientific Pub Co Pte Lt
Date: 02-2011
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2020
Publisher: ACM
Date: 14-05-2007
Publisher: Springer Berlin Heidelberg
Date: 2000
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2004
Publisher: Springer Berlin Heidelberg
Date: 2011
Publisher: Springer Science and Business Media LLC
Date: 10-08-2010
Publisher: Springer London
Date: 2004
Publisher: Springer US
Date: 2010
Publisher: Springer Berlin Heidelberg
Date: 2001
Publisher: ACM
Date: 24-10-2011
Publisher: Springer Berlin Heidelberg
Date: 2004
Publisher: Springer International Publishing
Date: 2018
Publisher: Springer Berlin Heidelberg
Date: 2001
Publisher: Springer Berlin Heidelberg
Date: 2001
Publisher: IEEE
Date: 07-2016
Publisher: Springer US
Date: 12-12-2009
Publisher: IEEE
Date: 05-2016
Publisher: Springer US
Date: 12-12-2009
Publisher: IEEE
Date: 2002
Publisher: Springer US
Date: 12-12-2009
Publisher: IEEE
Date: 12-2016
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11941439_120
Publisher: Springer Berlin Heidelberg
Date: 2009
Start Date: 12-2019
End Date: 12-2023
Amount: $600,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 04-2004
End Date: 06-2007
Amount: $129,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2016
End Date: 07-2020
Amount: $520,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 01-2010
End Date: 11-2012
Amount: $330,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 01-2007
End Date: 12-2009
Amount: $469,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 11-2010
End Date: 12-2013
Amount: $300,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 09-2015
End Date: 10-2015
Amount: $510,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2014
End Date: 09-2017
Amount: $382,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2012
End Date: 05-2015
Amount: $380,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2018
End Date: 12-2022
Amount: $373,733.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2022
End Date: 12-2025
Amount: $345,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2010
End Date: 12-2013
Amount: $335,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2014
End Date: 09-2017
Amount: $390,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 02-2009
End Date: 12-2011
Amount: $328,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2014
End Date: 07-2015
Amount: $1,000,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 02-2006
End Date: 12-2009
Amount: $246,000.00
Funder: Australian Research Council
View Funded Activity