Title: Mining from Big Graph Data: Theory, System and Practice

Reporter: Dr. Zhenguo Li, Researcher at Huawei (Hong Kong) Noah's Art Lab

Time:  9:30AM-11:00AM, 29 April 2016

Address:3-202, Building No. 5, School of Remote Sensing and Information Engineering, Wuhan University



In this talk, I will introduce the graph mining project in Huawei Noah's Ark Lab. I will present a unifying learning framework for graph data and show how it can shed new insights into various existing graph models, including PageRank, Label Propagation, Hitting Times, and Pseudo-inverse of Graph Laplacian. I will talk about graph model design, model comparison, and model selection, and highlight a variety of applications, including retrieval, classification, salient object detection, and APP recommendation, demonstrating its significant advancement over the state-of-the-art. Finally, I will present VENUS, a disk-based graph computation system which is able to handle billion-scale graphs efficiently on a commodity PC. For example, to run the PageRank algorithm on a Twitter graph of 42 million vertices and 1.4 billion edges, Spark needs 8.1 minutes with 50 machines and GraphChi spends 13 minutes using high-speed SSD, while VENUS only takes 5 minutes on one machine with an ordinary hard disk.


Dr. Zhenguo Li is a researcher in Huawei Noah’s Ark Lab at Hong Kong. He received the B.S. and M.S. degrees from the Department of Mathematics at Peking University, in 2002 and 2005, respectively, and the Ph.D. degree from the Department of Information Engineering at the Chinese University of Hong Kong, in 2008. He was an associate research scientist in the Department of Electrical Engineering at Columbia University. His research interests include machine learning and artificial intelligence, with a focus on graph-based approach. His research results have been published in top-tier conferences and journals including NIPS, ICML, CVPR, ICCV, VLDB, ICDE, TPAMI, and TKDE.

Presented by Dr. Zhenguo Li

PhD Recruitment of Huawei Noah's Ark Lab at Hong Kong:

Presented by Dr. Zhenguo Li