海韵讲座第85期

报告题目：On Learning for Combinatorial Optimization: Neural Graph Matching and Beyond

主讲人： Dr. Junchi Yan  上海交通大学

讲座时间： 2019年12月21日 9：00

讲座地点：  海韵园行政楼C505

报告内容摘要：

Learning for optimization has been an emerging direction for its potential for solving real-world decision-making problems, especially for those combinatorial optimization tasks with NP-hard nature. In this talk, I will first give a brief introduction on graph matching, which is a combinatorial problem in nature. Then I will show a deep network-based pipeline for direct learning of Lawler's QAP and its extension to hypergraph matching and multiple-graph matching. Our recent works on joint graph matching with cut, clustering, link prediction, and incremental multiple graph matching will also be reported. In the end, some discussion will be given on the future work and outlook for connecting graph matching and learning to optimize.

主讲人简介：

Dr. Junchi Yan is currently a tenure-track Associate Professor with Department of Computer Science and Engineering, and AI Institute, Shanghai Jiao Tong University. He is also the program director for the prestigious SJTU ACM Class (for AI direction). Before that, he was a Senior Research Staff Member (Principal Scientist) with IBM Research - China and IBM Thomas J. Watson Research Center, where he started his career since April 2011, and once an adjunct professor with the School of Data Science, Fudan University. His research interests are machine learning and computer vision. He serves as an Associate Editor for IEEE ACCESS, (Managing) Guest Editor for IEEE Transactions on Neural Network and Learning Systems, Pattern Recognition Letters, Pattern Recognition. He has published 50+ peer reviewed papers in top venues in AI and has filed 20+ US patents. He won the Distinguished Young Scientist of Scientific Chinese for year 2018 and CCF Outstanding Doctoral Thesis.