Title of the Report:Theoretical Methods and Applications of Clustering Analysis

Presenter:Liu Xinwang

Affiliation:National University of Defense Technology

Date of the Report:July 13, 2024 (Saturday), 14:45-15:30

Location of the Report: Fifth Conference Room on the First Floor, Block A, Feicui Science and Education Building

Abstract:Addressing the challenges of data diversity, incompleteness, and weak learnability in clustering analysis, this report will introduce a series of innovative achievements made by the research group in multi-view clustering fusion mechanisms, incomplete multi-view clustering, and deep clustering. It establishes new theories on how to fully utilize different types of features to improve clustering performance, proposes new methods for clustering imputation to deal with incomplete multi-view clustering, and explores new applications of learning features from raw data to optimally serve clustering. Continuous clustering analysis will be carried out to address the dynamic changes of data.

Biography of the Presenter:Recipient of the National Natural Science Foundation of China's Distinguished Youth Fund and Excellent Youth Fund. His main research interests include machine learning, data mining, etc. In the past five years, he has published more than 80 papers as the first or corresponding author in CCF A-level top journals and conferences, including 10 papers in IEEE TPAMI, including 3 as sole author. There are 12 ESI highly cited papers. His Google Scholar citations exceed 17,000 times, and he was selected into the list of top 2% of scientists globally for 2022-2023. He serves as an associate editor for journals such as IEEE TNNLS, IEEE TCYB, and information Fusion and as a senior program committee member/area chair for top conferences such as ICML, NeurIPS. Some of his research achievements have won the Hunan Provincial Natural Science First Prize twice (2nd of 6, 6th of 6).