Semi-Supervised Learning with Adversarially Missing Label Information

Loading...
Thumbnail Image
Penn collection
Departmental Papers (CIS)
Degree type
Discipline
Subject
Computer Sciences
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Syed, Umar
Contributor
Abstract

We address the problem of semi-supervised learning in an adversarial setting. Instead of assuming that labels are missing at random, we analyze a less favorable scenario where the label information can be missing partially and arbitrarily, which is motivated by several practical examples. We present nearly matching upper and lower generalization bounds for learning in this setting under reasonable assumptions about available label information. Motivated by the analysis, we formulate a convex optimization problem for parameter estimation, derive an efficient algorithm, and analyze its convergence. We provide experimental results on several standard data sets showing the robustness of our algorithm to the pattern of missing label information, outperforming several strong baselines.

Advisor
Date of presentation
2010-12-01
Conference name
Departmental Papers (CIS)
Conference dates
2023-05-17T07:08:14.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Syed, U., Taskar, B. (2010) Semi-supervised learning with adversarially missing label information. Advances in Neural Information Processing Systems 24 (NIPS 2010) http://www.cs.princeton.edu/%7Eusyed/SyedTaskarNIPS2010.pdf
Recommended citation
Collection