“A Unifying Framework for Learning Bayesian Network Structures
from Data: Block Learning Algorithm"

Tuesday, March 29, 2005
11:00 a.m. – 12:00 noon
Room 403, IS Building

You are invited to meet the speaker before the talk
from 10:30 AM – 11:00 AM in the Large Commons Room of the IS Building

Abstract: We present a block learning algorithm for learning large Bayesian network structures from sparse data in a distributed fashion. Adopting divide-and-conquer strategy, firstly, the block learning algorithm discovers local structures of Bayesian networks individually with preferred learning techniques.  After that, the learned local structures are combined together to recover the final Bayesian network. A series of experiments demonstrate that the block learning algorithm is able to learn a large Bayesian network structure from a small data set. Moreover, this algorithm is scalable and is capable to encompass the existing learning techniques. A study on the learning granularity, the learning engine and the algorithm design discovers that the block learning algorithm provides a uniform view on various learning techniques. Consequently, a unifying learning framework is built on the basis of the block learning algorithm.

Contact Information:
E-Mail: g0202313@nus.edu.sg
Homepage Link: http://enterprise.ise.nus.edu.sg/~g0202313/index.htm

Bio: Mr. Yi-Feng Zeng is currently a PhD candidate in the Department of Industrial and Systems Engineering, Faculty of Engineering, at National University of Singapore (NUS), in the final phase of his dissertation work. He received his M.Sc. degree in Computer and Information Engineering at Xia'men University, China in 2002. Now, he is doing his PHD research work in Bio-medical Decision Engineering (BiDE) Group, School of Computing, at NUS. His current research interests include Bayesian network leaning, normative multi-agent decision making and systems biology.