2015 ReducingtheUnlabeledSampleCompl

• (Lan & Huan, 2015) ⇒ Chao Lan, and Jun Huan. (2015). “Reducing the Unlabeled Sample Complexity of Semi-Supervised Multi-View Learning.” In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2015). ISBN:978-1-4503-3664-2 doi:10.1145/2783258.2783409

Subject Headings:

Cited By

• http://scholar.google.com/scholar?q=%222015%22+Reducing+the+Unlabeled+Sample+Complexity+of+Semi-Supervised+Multi-View+Learning
• http://dl.acm.org/citation.cfm?id=2783258.2783409&preflayout=flat#citedby

Quotes

Author Keywords

• Concept learning; general; multi-view learning; sample complexity; semi-supervised learning

Abstract

In semi-supervised multi-view learning, unlabeled sample complexity (u.s.c.) specifies the size of unlabeled training sample that guarantees a desired learning error. In this paper, we improve the state-of-art u.s.c. from O (1/ε) to O (log 1/ε) for small error ε, under mild conditions. To obtain the improved result, as a primary step we prove a connection between the generalization error of a classifier and its incompatibility, which measures the fitness between the classifier and the sample distribution. We then prove that with a sufficiently large unlabeled sample, one is able to find classifiers with low incompatibility. Combining the two observations, we manage to prove a probably approximately correct (PAC) style learning bound for semi-supervised multi-view learning. We empirically verified our theory by designing two proof-of-concept multi-view learning algorithms, one based on active view sensing and the other based on online co-regularization, with real-world data sets.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2015 ReducingtheUnlabeledSampleCompl	Jun Huan Chao Lan			Reducing the Unlabeled Sample Complexity of Semi-Supervised Multi-View Learning				10.1145/2783258.2783409		2015