An Information Theoretic Framework for Multi-view Learning

In the multi-view learning paradigm, the input variable is partitioned into two different views X1 and X2 and there is a target variable Y of interest. The underlying assumption is that either view alone is sufficient to predict the target Y accurately. This provides a natural semi-supervised learning setting in which unlabeled data can be used to eliminate hypothesis from either view, whose predictions tend to disagree with predictions based on the other view. This work explicitly formalizes an information theoretic, multi-view assumption and studies the multi-view paradigm in the PAC style semisupervised framework of Balcan and Blum [2006]. Underlying the PAC style framework is that an incompatibility function is assumed to be known -roughly speaking, this incompatibility function is a means to score how good a function is based on the unlabeled data alone. Here, we show how to derive incompatibility functions for certain loss functions of interest, so that minimizing this incompati...

• Type: Conference
• Year: 2008
• Where: COLT
• Authors: Karthik Sridharan, Sham M. Kakade
• Keywords: COLT 2008, Incompatibility Functions, Machine Learning, Multi-view Assumption, Unlabeled Data