报告题目: Systems and Algorithms for Big Data Analytics

报告人：严达 博士（阿拉巴马大学 助理教授）

主持人：王晓玲 教授

报告时间：2016年5月16日 下午13:00-14:30

报告地点：中北校区数学馆201报告厅

报告摘要：

We are now in the Big Data era, and scalable techniques for efficient big data analytics are in high demand. This talk introduces the latest development in the field of big data analytics systems, with a special focus on graph processing systems. Google's Pregel is a pioneering distributed framework for big graph analytics, and has inspired numermous research on big graph systems since its advent in 2010. This talk starts with a brief review on Pregel, and then introduces how to develop graph algorithms for various applications under the model of Pregel with performance guarantees. We then proceed to identify the weaknesses of the existing model of Pregel in processing large real graphs, and introduce a novel block-centric computation model that improves the performance by orders of magnitude. We also briefly cover other important improvements to Pregel, including communication mechanism, on-demand querying, out-of-core support, fault tolerance, etc. Many of the introduced works have been published in first-tier conferences, including four recent VLDB papers and one recent WWW paper. Finally, the talk will also touch upon scalable techniques for processing other types of big data such as geo-spatial data and uncertain data, and provide a vision on future directions of big data research.

报告人简介：

Dr. YAN, Da will join the University of Alabama at Birmingham as an assistant professor in Aug, 2016, He received his Ph.D. degree in Computer Science from the Hong Kong University of Science and Technology in 2014, and is currently a postdoctoral fellow in the Chinese University of Hong Kong. He is the winner of Hong Kong 2015 Young Scientist Award in Physical/Mathematical Science.

Dr. YAN's research focuses on the development of scalable systems and algorithms for big data analytics, with a special emphasis on graph data, geo-spatial data and data uncertainty. The results of his research have been published in top-tier conferences such as SIGMOD, SIGKDD, ICDE, EDBT, and top-tier journals such as PVLDB and TKDE. Notably, his first research paper won the best paper award in the 2011 DASFAA conference. His research has been awarded with ITF and GRF grants, and the systems he developed have been used by many research groups as well as companies (e.g., Taobao).