Slides available here!

Speaker:

Prof. Wenguang Chen, Tsinghua University, China

Title:

Single Node Machine Learning Systems - When big data meet Moore's Law

Abstract:

Today, it is popular to process big data with distributed machines, because the working set of big data analysis is usually larger than the memory size of a single machine. However, a large portion of big data analysis problems has the almost fixed problem size, e.g. social network analysis and gene assembly. The Moore's law is improving the memory size and processing power of a single machine exponentially, indicating that many today's big data problems will become tomorrow's small data problem. Single node machine learning systems with out-of-core support is a bridge between now and future. We introduce GridGraph, our recent research on out-of-core machine learning systems, which is an order of magnitude more cost-efficient than the state-of-the-art distributed machine learning systems such as GraphLab and GraphX.

Bio:

Wenguang Chen received the B.S. and Ph.D. degrees in computer science from Tsinghua University in 1995 and 2000 respectively. He was the CTO of Opportunity International Inc. from 2000-2002. Since January 2003, he joined Tsinghua Univeristy. He is now a professor in Department of Computer Science and Technology, Tsinghua University. His research interest is in distributed computing, programming model and social network analysis. He is now a distinguished member of CCF, a member of ACM. He serves as editor-in-chief of Communication of ACM, China Edition.



* If you wish to modify any information or update your photo, please contact the web chairmpsoc2014@imag.fr