Learning for graph matching and beyond 图匹配的机器学习求解

Speaker:   Prof. Junchi Yan

Time:       10:00-11:00, Sep. 5

Location:  SIST 1A 200

Host:       Prof. Jingyi Yu

 

Abstract:

In this talk, I will first give a brief introduction on graph matching, which is a combinatorial problem in nature. Then we will show a deep network based pipeline for addressing the graph matching problem via deep learning. The model involves learning of the graph node embedding, cross-graph affinity learning, and a Sinkhorn layer for solving the linear assignment task. We will also discuss some working paper on joint matching and link prediction among two or multiple graphs. In the end, some discussion will be given on the future work and outlook for connecting graph matching with machine learning.

Bio:

Dr. Junchi Yan is currently an Independent Research Professor (PhD Advisor) with Department of Computer Science and Engineering, Shanghai Jiao Tong University. He is also affiliated with The Artificial Intelligence Institute of SJTU and an adjunct professor with the School of Data Science, Fudan University. Before that, he was a Research Staff Member with IBM Research - China where he started his career since April 2011. He obtained the Ph.D. at the Department of Electronic Engineering of Shanghai Jiao Tong University, China. His work on graph matching received the ACM China Doctoral Dissertation Nomination Award and China Computer Federation Doctoral Dissertation Award. His research interests are machine learning, data mining 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, Vice Secretary of China CSIG-BVD Technical Committee, and on the executive board of ACM China Multimedia Chapter. He has published 50+ peer reviewed papers in top venues in AI and has filed 20+ US patents. He wins the Distinguished Young Scientist of Scientific Chinese for year 2018.

 

严骏驰博士现任上海交通大学计算机系与人工智能研究院特别研究员(博导),交大ACM班项目副主任(负责AI方向),复旦大学大数据学院校外研究生导师。主持包括国家自然科学基金、以及与招行、银联、腾讯、京东、平安等在内多项合作研究项目。曾于IBM(北京、纽约、上海)任职7年。加入上海交大之前,任IBM中国研究院主管研究员(认知物联网首席科学家)和复旦大学大数据学院校外导师,主导了多项人工智能技术在国内外大型企业和政府创新应用的研发与落地。近年来的研究工作致力于精细化数据建模与机器学习,在结构信息匹配与识别方面发表NIPS,CVPR,ICCV,ECCV,ACM-MM,AAAI,TIP,TCYB,TPAMI论文20余篇;在时序信息建模与学习发表NIPS,SIGIR,KDD,AAAI,IJCAI发表论文20余篇。授权美国发明专利15项,连续两届被评为IBM全球发明大师。现任中国图象图形学学会视觉大数据专委会副秘书长、ACM中国SIGMM执委、IEEE TNNLS期刊责任客座编辑、Pattern Recognition期刊客座编辑、IEEE ACCESS期刊编委,曾任IBM美国沃森研究中心、日本国立情报学研究所、腾讯/京东人工智能实验室等机构访问学者。严骏驰博士也是2018年度科学中国人杰出青年科学家奖和2016年度CCF优博的获得者。

SIST-Seminar 18197