ORCID Profile
0000-0002-1262-4174
Current Organisation
Harbin Institute of Technology (Shenzhen)
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.
Publisher: Elsevier BV
Date: 11-2022
Publisher: Association for Computing Machinery (ACM)
Date: 13-06-2023
DOI: 10.1145/3589316
Abstract: Due to the sweeping digitalization of processes, increasingly vast amounts of time series data are being produced. Accurate classification of such time series facilitates decision making in multiple domains. State-of-the-art classification accuracy is often achieved by ensemble learning where results are synthesized from multiple base models. This characteristic implies that ensemble learning needs substantial computing resources, preventing their use in resource-limited environments, such as in edge devices. To extend the applicability of ensemble learning, we propose the LightTS framework that compresses large ensembles into lightweight models while ensuring competitive accuracy. First, we propose adaptive ensemble distillation that assigns adaptive weights to different base models such that their varying classification capabilities contribute purposefully to the training of the lightweight model. Second, we propose means of identifying Pareto optimal settings w.r.t. model accuracy and model size, thus enabling users with a space budget to select the most accurate lightweight model. We report on experiments using 128 real-world time series sets and different types of base models that justify key decisions in the design of LightTS and provide evidence that LightTS is able to outperform competitors.
Publisher: Association for Computing Machinery (ACM)
Date: 26-05-2023
DOI: 10.1145/3588951
Abstract: Sensors in cyber-physical systems often capture interconnected processes and thus emit correlated time series (CTS), the forecasting of which enables important applications. The key to successful CTS forecasting is to uncover the temporal dynamics of time series and the spatial correlations among time series. Deep learning-based solutions exhibit impressive performance at discerning these aspects. In particular, automated CTS forecasting, where the design of an optimal deep learning architecture is automated, enables forecasting accuracy that surpasses what has been achieved by manual approaches. However, automated CTS solutions remain in their infancy and are only able to find optimal architectures for predefined hyperparameters and scale poorly to large-scale CTS. To overcome these limitations, we propose AutoCTS+, a joint, scalable framework, to automatically devise effective CTS forecasting models. Specifically, we encode each candidate architecture and accompanying hyperparameters into a joint graph representation. We introduce an efficient Architecture-Hyperparameter Comparator (AHC) to rank all architecture-hyperparameter pairs, and we then further evaluate the top-ranked pairs to select an architecture-hyperparameter pair as the final model. Extensive experiments on six benchmark datasets demonstrate that AutoCTS+ not only eliminates manual efforts but also is capable of better performance than manually designed and existing automatically designed CTS models. In addition, it shows excellent scalability to large CTS.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2021
Publisher: International Joint Conferences on Artificial Intelligence Organization
Date: 07-2020
Abstract: One-Shot Neural architecture search (NAS) has received wide attentions due to its computational efficiency. Most state-of-the-art One-Shot NAS methods use the validation accuracy based on inheriting weights from the supernet as the stepping stone to search for the best performing architecture, adopting a bilevel optimization pattern with assuming this validation accuracy approximates to the test accuracy after re-training. However, recent works have found that there is no positive correlation between the above validation accuracy and test accuracy for these One-Shot NAS methods, and this reward based s ling for supernet training also entails the rich-get-richer problem. To handle this deceptive problem, this paper presents a new approach, Efficient Novelty-driven Neural Architecture Search, to s le the most abnormal architecture to train the supernet. Specifically, a single-path supernet is adopted, and only the weights of a single architecture s led by our novelty search are optimized in each step to reduce the memory demand greatly. Experiments demonstrate the effectiveness and efficiency of our novelty search based architecture s ling method.
Publisher: ACM
Date: 30-04-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2021
No related grants have been discovered for Miao Zhang.