Privacy-Aware and Personalised Explanation Overlays for Recommender Systems. AI-powered recommender systems provide recommendations for daily lives, but they need to be legally interpretable and explainable. This project aims to transform existing black-box recommender models into transparent and trustworthy decision-support systems. The resulting tools will offer granular, explorable rationales for the recommendations in real time, creating greater public confidence while advancing the field. ....Privacy-Aware and Personalised Explanation Overlays for Recommender Systems. AI-powered recommender systems provide recommendations for daily lives, but they need to be legally interpretable and explainable. This project aims to transform existing black-box recommender models into transparent and trustworthy decision-support systems. The resulting tools will offer granular, explorable rationales for the recommendations in real time, creating greater public confidence while advancing the field. The expected outcomes include graph embedding methods for capturing real-world relationships in all their messiness and complexity. The anticipated contributions include impartial and accountable recommender models that are resistant to adversarial attacks and that slow the spread of misinformation.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230101033
Funder
Australian Research Council
Funding Amount
$420,154.00
Summary
Scalable and Lightweight On-Device Recommender Systems. This project aims to address the resource-intensive and non-resilient nature of existing cloud-based personalised recommendation services. This project expects to generate new knowledge in the intersection of on-device machine learning and recommender systems. The expected outcomes include a novel auto-deployment platform that can efficiently customise a model for each user device's configuration, supporting on-device recommendation and mod ....Scalable and Lightweight On-Device Recommender Systems. This project aims to address the resource-intensive and non-resilient nature of existing cloud-based personalised recommendation services. This project expects to generate new knowledge in the intersection of on-device machine learning and recommender systems. The expected outcomes include a novel auto-deployment platform that can efficiently customise a model for each user device's configuration, supporting on-device recommendation and model updates with tiny computational footprints. The benefits of these outcomes will position Australia at the forefront of AI and give numerous businesses the tools needed to deploy innovative business systems with a secure and cost-effective advantage.Read moreRead less
Knowledge Graph-driven Software Vulnerability Risk Discovery and Assessment. This project aims to alleviate cyberattacks which are increasingly being crafted to attack software vulnerabilities and weaknesses by utilising advanced knowledge graphs and deep learning techniques. This project expects to construct an innovative software vulnerability knowledge graph and develop advanced graph-based algorithms and models. Expected outcomes of this project include the enhanced capacity to defend agains ....Knowledge Graph-driven Software Vulnerability Risk Discovery and Assessment. This project aims to alleviate cyberattacks which are increasingly being crafted to attack software vulnerabilities and weaknesses by utilising advanced knowledge graphs and deep learning techniques. This project expects to construct an innovative software vulnerability knowledge graph and develop advanced graph-based algorithms and models. Expected outcomes of this project include the enhanced capacity to defend against cyberattacks for both organisations and individuals in Australia and beyond, theory development in graph theory, refined graph neural network models and improved graph transfer learning algorithms.Read moreRead less
Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models ....Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models, based on the incorporation of an explicit searchable memory, which will dramatically reduce model size, hardware requirements and energy usage. This will make modern natural language processing more accessible, while also providing greater flexibility, allowing for more adaptable and portable technologies.Read moreRead less
Responsible modelling respecting privacy, data quality, and green computing. With the unprecedented growing impact of data on science, the economy and society, there comes the need for responsible data science practices which are accountable for the social good. This project aims to investigate the challenging problem of how to provide responsible data management, spanning across privacy-aware data exploration, resilient modelling to cope with imperfect data, and efficient model architectures fo ....Responsible modelling respecting privacy, data quality, and green computing. With the unprecedented growing impact of data on science, the economy and society, there comes the need for responsible data science practices which are accountable for the social good. This project aims to investigate the challenging problem of how to provide responsible data management, spanning across privacy-aware data exploration, resilient modelling to cope with imperfect data, and efficient model architectures for resource-constrained environments. This will be achieved by developing theories and techniques for complex real-world multi-modal data retrieval throughout the data life-cycle. The expected outcomes will significantly contribute to building capability in emerging technologies in the context of responsible data science. Read moreRead less
Personalised Privacy-Preserving Network Data Publishing System . Data sharing has become a driving force for many businesses in industrial sectors. This project aims to develop a privacy preserving network data publishing system that can preserve user privacy in a personalised way while maintaining maximal utility of the published data. To make accurate privacy preservation, this project will design novel learning models to derive accurate users’ correlation and their privacy intention, develop ....Personalised Privacy-Preserving Network Data Publishing System . Data sharing has become a driving force for many businesses in industrial sectors. This project aims to develop a privacy preserving network data publishing system that can preserve user privacy in a personalised way while maintaining maximal utility of the published data. To make accurate privacy preservation, this project will design novel learning models to derive accurate users’ correlation and their privacy intention, develop efficient privacy preserving algorithms to deal with static and dynamic network data sharing. The success of this project will benefit many industries and government agencies to reduce users’ privacy breaches, avoid illegal consequences of sharing data, and enhance these service providers’ service quality.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230101329
Funder
Australian Research Council
Funding Amount
$432,355.00
Summary
Trading Privacy, Bandwidth and Accuracy in Algorithmic Machine Learning. This project aims to investigate the trade-offs between privacy, communication costs and accuracy of results when learning from users' sensitive data. The project intends to design faster and more accurate algorithms for a wide range of machine learning tasks by developing a novel and widely-applicable algorithmic framework. Expected outcomes of this project include new theoretical tools to guide the design of data-driven d ....Trading Privacy, Bandwidth and Accuracy in Algorithmic Machine Learning. This project aims to investigate the trade-offs between privacy, communication costs and accuracy of results when learning from users' sensitive data. The project intends to design faster and more accurate algorithms for a wide range of machine learning tasks by developing a novel and widely-applicable algorithmic framework. Expected outcomes of this project include new theoretical tools to guide the design of data-driven decision systems and rigorously analyse their performance and privacy guarantees. Privacy of individuals' information in data analytics pipelines is a key societal concern. This project should lead to significant benefits by strengthening privacy in these pipelines while also improving accuracy and cost-efficiency.Read moreRead less
Deep Adder Networks on Edge Devices. This project aims to empower edge devices with intelligence by developing advanced deep neural networks that address the conflict between the high resource requirements of deep learning and the generally inadequate performance of the edge. Multiplication has been the dominant type of operation in deep learning, though the addition is known to be much cheaper. This project expects to yield theories and algorithms that allow deep neural networks consisting of n ....Deep Adder Networks on Edge Devices. This project aims to empower edge devices with intelligence by developing advanced deep neural networks that address the conflict between the high resource requirements of deep learning and the generally inadequate performance of the edge. Multiplication has been the dominant type of operation in deep learning, though the addition is known to be much cheaper. This project expects to yield theories and algorithms that allow deep neural networks consisting of nearly pure additions to fulfil the requisites of accuracy, robustness, calibration and generalisation in real-world computer vision tasks. The success of this project will benefit deep learning-based products on smartphones or robots in health and cybersecurity.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230101591
Funder
Australian Research Council
Funding Amount
$419,154.00
Summary
Towards Real-world Continual Learning on Unrestricted Task Steams. This project aims to enable machines to continually learn without forgetting and accumulate knowledge from the sequential data streams containing diverse tasks. This project expects to advance the continual learning to unrestricted real-world task steams that are long-term and complex and promote artificial intelligence toward the human-level intelligence that can automatically evolve during interaction with the world. Expected o ....Towards Real-world Continual Learning on Unrestricted Task Steams. This project aims to enable machines to continually learn without forgetting and accumulate knowledge from the sequential data streams containing diverse tasks. This project expects to advance the continual learning to unrestricted real-world task steams that are long-term and complex and promote artificial intelligence toward the human-level intelligence that can automatically evolve during interaction with the world. Expected outcomes of this project include the paradigm-shifting continual learning framework and techniques for handling unrestricted task steams in real-world scenarios. They will benefit society and the economy nationally and internationally by enhancing the applicability of artificial intelligence.Read moreRead less
Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training ....Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training, which are anticipated to deepen our understanding of visual representation and make it easier to build and deploy computer vision applications and services. Examples of benefits include modernising machines in manufacturing and farming with visual intelligence. Read moreRead less