Researcher Wu Min from the Singapore Agency for Science, Technology and Research was specially invited to the school to give an academic report.

On the afternoon of June 5, Nanjing University of Information Science & Technology - Zhongda Hospital Smart Medical Research Institute invited Researcher Wu Min from the Agency for Science, Technology and Research (A*STAR) of Singapore to come to the school to give an academic report titled “Label-efficient Time Series Representation Learning”. Professor Xu Jun, deputy dean of the School of Artificial Intelligence (College of Future Technology) and executive director of the Smart Medical Research Institute of our school, presided over this report meeting. This meeting adopted a combination of offline + online (Tencent Conference and Koxiang Academic). There were more than 100 teachers and students participating in the meeting, including 2,026 live broadcasts of Koxiang Academic.

Researcher Wu Min’s report mainly introduced some achievements in label-efficient time series data analysis: 1) self-supervised representation learning; (2) time series data domain adaptation; and (3) related applications (including sleep detection and computational biology). Dr. Wu first introduced a set of unsupervised representation learning framework for time series data, which mainly includes temporal contrast learning and context contrast learning modules, which can effectively learn effective representations from unsupervised time series signals and extend the semi-supervised representation learning framework based on category information. Then, Dr. Wu introduced the time series domain adaptation method based on sensor alignment, which designed a spatio-temporal alignment method based on graph networks and achieved good domain adaptation effects. Dr. Wu also introduced the time series domain adaptive benchmark evaluation suite ADATIME developed by his team, which provides a complete process of data preprocessing, algorithm, evaluation and testing. Finally, Dr. Wu introduced some application results, including self-supervised sleep monitoring algorithms and graph network research results in computational biology.

The academic atmosphere was strong during the report period. During the interactive session, participating teachers and students actively asked questions and had extensive and in-depth exchanges with Dr. Wu on the application of time series data in medical data processing, the progress of self-adaptation in the field of time series prediction tasks, the prospects of graph networks in single cell analysis, and optimization of self-supervised algorithms. The academic atmosphere at the venue was strong.

Introduction to Researcher Wu Min

Dr. Wu Min is currently a senior research scientist in the machine intelligence department of the Agency for Science, Technology and Research (A*STAR) of Singapore. Research areas include machine learning and data mining of time series data and graph data. degree in computer science from Nanyang Technological University (NTU), Singapore, in 2011 and the bachelor’s degree in computer science from the University of Science and Technology of China (USTC) in 2006, respectively. He has won the best paper award at 2022 IEEE ICIEA, 2022 IEEE SmartCity, 2016 InCoB and 2015 DASFAA, as well as the shortlisted academic paper award at 2020 IEEE PHM, and won the championship of the 2021 CVPR UG2+ Challenge and the 2015 IJCAI competition on repeated buyers prediction respectively.

Translated from the original Chinese source.