Institute of Information Science, Academia Sinica

It is widely accepted that machines can learn just like a normal human being does: feeding a learning algorithm with sufficient amount of training data, it can generate a model that transforms the inputs to the outputs. Discovery, on the other hand, is about finding something for the first time, which has never been observed in the training data. One interesting question to ask is whether machines can perform discovery when there is no labelled data available. In this talk, I will introduce several of our recent findings in this direction, including identifying novel social links between users and items; finding missing correspondences between objects across domains using only rating data; inferring sensor values of unobserved locations; and deciphering the secret key in Cryptography, etc. Such findings show that with the availability of large unlabeled data and powerful computation infrastructure, machines can indeed perform discovery tasks.

Shou-de Lin is currently an associate professor in the CSIE department of National Taiwan University. He holds a BS in EE department from National Taiwan University, an MS-EE from the University of Michigan, and an MS in Computational Linguistics and PhD in Computer Science both from the University of Southern California. He leads the Machine Discovery and Social Network Mining Lab in NTU. Before joining NTU, he was a post-doctoral research fellow at the Los Alamos National Lab.

Prof. Lin's research includes the areas of machine learning and data mining, social network analysis, and natural language processing. His international recognition includes the best paper award in IEEE Web Intelligent conference 2003, Google Research Award in 2007, Microsoft research award in 2008, merit paper award in TAAI 2010, best paper award in ASONAM 2011, US Aerospace AFOSR/AOARD research award winner from 2011 and 2013, 2014. He is the all-time winners in ACM KDD Cup, leading or co-leading the NTU team to win championships in 2008 (co-champion with IBM Research), 2010 (student team champion and overall team champion), 2011 (dual champions in both tracks), 2012 (track 2 champion), 2013 (double champions in both track), and ranked 2nd in 2003 and 3rd in 2009. He has served as the senior PC for SIGKDD and area chair for ACL. He is currently the associate editor for International Journal on Social Network Mining, Journal of Information Science and Engineering, and International Journal of Computational Linguistics and Chinese Language Processing.