This event has passed.
Friday, February 5, 2021 – 7:00AM to 8:00AM
Xuehai Qian, Assistant Professor Ming Hsieh Department of Electrical and Computer Engineering University of Southern California
Graph mining, which finds all embeddings matching specific patterns, is a fundamental task in many applications. In this talk, I will present the first graph mining system that decomposes the target pattern into several subpatterns, and then computes the count of each. The system addressed several key challenges including: a partial-embedding-centric programming model supporting advanced graph mining applications; an accurate and efficient cost model based on approximate graph mining; an efficient search method to jointly determine the decomposition of all concrete patterns of an application; and the partial symmetry breaking technique to eliminate redundant enumeration. Our experiments show that the system is significantly faster than all existing state-of-the-art systems and provides a novel and viable path to scale to large patterns. I will also introduce the instruction set extension and architectural supports for the key primitive, intersection, to accelerate graph mining algorithms.
Xuehai Qian is an assistant professor at the University of Southern California. His research interests include domain-specific systems and architectures for emerging applications such as machine learning and graph analytics, and recently hardware security and quantum computing. He got his Ph.D from UIUC. He is the recipient of W.J Poppelbaum Memorial Award at UIUC, NSF CRII and CAREER Award, and the inaugural ACSIC (American Chinese Scholar In Computing) Rising Star Award