Learning from Noisy Similar and Dissimilar Data

Abstract

With the widespread use of machine learning for classification, it becomes increasingly important to be able to use weaker kinds of supervision for tasks in which it is hard to obtain standard labeled data. One such kind of supervision is provided pairwise---in the form of Similar (S) pairs (if two examples belong to the same class) and Dissimilar (D) pairs (if two examples belong to different classes). This kind of supervision is realistic in privacy-sensitive domains. Although this problem has been looked at recently, it is unclear how to learn from such supervision under label noise, which is very common when the supervision is crowd-sourced. In this paper, we close this gap and demonstrate how to learn a classifier from noisy S and D labeled data. We perform a detailed investigation of this problem under two realistic noise models and propose two algorithms to learn from noisy S-D data. We also show important connections between learning from such pairwise supervision data and learning from ordinary class-labeled data. Finally, we perform experiments on synthetic and real world datasets and show our noise-informed algorithms outperform noise-blind baselines in learning from noisy pairwise data.

8 pages

References in corpus (5)

• MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
• Active Ranking using Pairwise Comparisons
• Query Complexity of Derivative-Free Optimization
• Learning from Binary Labels with Instance-Dependent Corruption
• Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization