Keynote Speakers

Prof. Haizhou Li
IEEE Fellow

National University of Singapore, Singapore

Haizhou Li is a Presidential Chair Professor and Associate Dean (Research) at the School of Data Science, The Chinese University of Hong Kong, Shenzhen, China. Dr. Li is also with the Department of Electrical and Computer Engineering, National University of Singapore (NUS), Singapore.

Dr. Li was the recipient of National Infocomm Awards 2002, Institution of Engineers Singapore (IES) Prestigious Engineering Achievement Award 2013 and 2015, President's Technology Award 2013, and MTI Innovation Activist Gold Award 2015 in Singapore. He was named one of the two Nokia Visiting Professors in 2009 by Nokia Foundation, IEEE Fellow in 2014 for leadership in multilingual, speaker and language recognition, ISCA Fellow in 2018 for contributions to multilingual speech information processing, and Bremen Excellence Chair Professor in 2019. Dr. Li is a Fellow of Academy of Engineering Singapore.

Speech Title: Seeing to Hear Better
Abstract: Humans have a remarkable ability to pay their auditory attention only to a sound source of interest, that we call selective auditory attention, in a multi-talker environment or a Cocktail Party. However, signal processing approach to speech separation and/or speaker extraction from multi-talker speech remains a challenge for machines. In this talk, we study the deep learning solutions to monaural speech separation and speaker extraction that enable selective auditory attention. We review the findings from human audio-visual speech perception to motivate the design of speech perception algorithms. We introduce their applications in speech enhancement, speaker extraction, and speech recognition. We will also discuss the computational auditory models, technical challenges and the recent advances in the field.

Prof. De-Shuang Huang
IEEE Fellow

EIT Institute for Advanced Study & Tongji University, China

De-Shuang Huang is a Professor in Institute of Machine Learning and Systems Biology, EIT Institute for Advanced Study, China and Tongji University, China. He is currently the Fellow of the IEEE (IEEE Fellow), the Fellow of the International Association of Pattern Recognition (IAPR Fellow), the Fellow of the Asia-Pacific Artificial Intelligence Association (AAIA), and associated editors of IEEE/ACM Transactions on Computational Biology & Bioinformatics and IEEE Transactions on Cognitive and Developmental Systems, etc. He founded the International Conference on Intelligent Computing (ICIC) in 2005. ICIC has since been successfully held annually with him serving as General or Steering Committee Chair. He also served as the 2015 International Joint Conference on Neural Networks (IJCNN2015) General Chair, July12-17, 2015, Killarney, Ireland, the 2014 11th IEEE Computational Intelligence in Bioinformatics and Computational Biology Conference (IEEE-CIBCBC) Program Committee Chair, May 21-24, 2014, Honolulu, USA. He has published over 470 papers in international journals, international conferences proceedings, and book chapters. Particularly, he has published over 240 SCI indexed papers. His Google Scholar citation number is over 20500 times and H index 76. His main research interest includes neural networks, pattern recognition and bioinformatics. His main research interest includes neural networks, pattern recognition and bioinformatics.

Speech Title: Representation Learning in Graph Neural Networks
Abstract: Graph Neural Networks (GNN) have achieved advanced performance in many fields such as traffic prediction, recommendation systems, and computer vision. Recently there are majorities of methods on GNN focusing on graph convolution, and less work about pooling. Existing graph pooling methods mostly are based on Top-k node selection, in which unselected nodes will be directly discarded, caused the loss of feature information. In that case, we propose a novel graph pooling operator called Hierarchical Graph Pooling with Self- Adaptive Cluster Aggregation (HGP-SACA), which uses a sparse and differentiable method to capture the graph structure. Before using top-k for cluster selection, the unselected clusters are aggregated by an n-hop, and the merged clusters are used for top-k selection, so that the merged clusters can contain neighborhood clusters enhancing the function of the unselected cluster. This can enhance the function of the unselected cluster. Through extensive theoretical analysis and experimental verification on multiple datasets, our experimental results show that combining the existing GNN architecture with HGP-SACA can achieve state-of-the-art results on multiple graph classification benchmarks, which proves the effectiveness of our proposed model. Besides, we also introduce our latest work which is the hierarchical graph pooling with adaptive multi-scale topology learning and node selection.

Prof. Alexander Gammerman
Royal Holloway, University of London, UK

Professor Gammerman's current research interest lies in machine learning and, in particular, in the development of conformal predictors -- a set of novel machine learning techniques that guarantee the validity of prediction. Areas in which these techniques have been applied include medical diagnosis, drug design, forensic science, proteomics, genomics, environment, and information security. He has published about two hundred research papers and several books on computational learning and probabilistic inference.

Professor Gammerman is a Fellow of the Royal Statistical Society and a Fellow of the Royal Society of Arts. He chaired and participated in organizing committees of many international conferences and workshops on Machine Learning and Bayesian methods in Europe, Russia and in the United States. He was also a member of the editorial boards of the Law, Probability and Risk journal (2002-2009) and the Computer Journal (2003-2008). He has held visiting and honorary professorships from several universities in Europe and USA. Further details can be found at

Speech Title: Conformal Prediction and Testing for Reliable Pattern Recognition
Abstract: The talk reviews a modern machine learning technique called Conformal Predictors. The approach has been motivated by the algorithmic notion of randomness and allows us to make reliable predictions with valid measures of confidence for individual examples. The developed technique guarantees that the overall accuracy can be controlled by a required confidence level. Unlike many conventional techniques, the approach does not make any additional assumption about the data beyond the i.i.d. assumption: the examples are independent and identically distributed. The way to test this assumption is described. The talk also outlines some generalisations of Conformal Predictors and their applications to many different fields including medicine, cheminformatics, information security, environment, plasma physics, home security and others.