Best Paper Award at CPAL 2024

Congratulations to Prof Ivor Tsang, Dr Pan Yuangang and Dr Yao Yinghua for being recognised with the Best Paper Award at the Conference on Parsimony and Learning (CPAL) 2024!

Organised by top-tier machine learning researchers in the community, CPAL aims to address the parsimonious that prevail in machine learning, signal processing, optimisation, and beyond.

While deep clustering methods have made significant improvements in clustering accuracy, existing approaches fall short of fulfilling requirements from other perspectives, such as universality, interpretability and efficiency, which are crucial with the emerging demand for diverse applications.

To address the research gap, the team introduced a new framework, named “PC-X: Profound Clustering via Slow Exemplars” which fulfills the four basic requirements of clustering: clustering accuracy, universality, interpretability, and efficiency. PC-X encodes data within the auto-encoder (AE) network, reducing its dependence on data modality (universality). Moreover, the Centroid-Integration Unit (CI-Unit) is designed to facilitate the suppression of sample-specific details for better representation learning (accuracy) and prompt clustering of centroids to become legible exemplars (interpretability). These exemplars are calibrated stably with mini-batch data following tailor-designed optimisation scheme and converges in linear (efficiency).

Findings from the paper hold promise to advance the field of deep clustering and interpretable machine learning. Congratulations to the team once again!

Read the full article.

Find out more about CPAL 2024.

About the team members:

Dr Pan Yuangang
Research Scientist

Dr Pan Yuangang is currently a research scientist at A*STAR’s Centre for Frontier AI Research (CFAR). Before joining A*STAR, he was a postdoctoral research associate at the Australian Artificial Intelligence Institute (AAII) at University of Technology Sydney (UTS). He completed his Ph.D. degree in Computer Science in Mar 2020 from University of Technology Sydney (UTS), Australia, under the supervision of Prof Ivor Tsang. He has authored and co-authored papers in various top journals, such as JMLR, IEEE TPAMI, IEEE TNNLS, IEEE TKDE, IEEE TIFS, MLJ, ACM TOIS and Hypertension. His research interests include (Non)parametric Clustering, Generative AI, AI for Science & Healthcare.

Dr Yao Yinghua
Research Scientist

Dr Yao Yinghua is a research scientist at A*STAR’s Centre for Frontier AI Research (CFAR). She obtained her Ph.D. in Sept. 2023 from the University of Technology Sydney (UTS), Australia, under the supervision of Prof Ivor Tsang and Prof Yao Xin. She has authored and co-authored papers on IEEE TNNLS, Machine Learning, and IEEE TPAMI. Her research focuses on Generative Models, Deep Clustering, and Generative AI for Bioscience.

Prof Ivor Tsang
Director

Prof Ivor W Tsang is Director of A*STAR Centre for Frontier AI Research (CFAR) since Jan 2022. He is also an Adjunct Professor at School of Computer Science and Engineering (SCSE), Nanyang Technological University, Singapore. Previously, he was a Professor of Artificial Intelligence, at University of Technology Sydney (UTS), and Research Director of the Australian Artificial Intelligence Institute (AAII), the largest AI institute in Australia, which is the key player to drive the University of Technology Sydney to rank 10th globally and 1st in Australia for AI research, in the latest AI Research Index. Prof Tsang is working at the forefront of big data analytics and Artificial Intelligence. His research focuses on transfer learning, deep generative models, learning with weakly supervision, big data analytics for data with extremely high dimensions in features, samples and labels. He was elected to the 2022 class of IEEE Fellows for his contributions to those fields.