Formal Models of Active Learning from Contrastive Examples
Farnam Mansouri, Hans U. Simon, Adish Singla, Yuxin Chen, Sandra Zilles
Abstract
Machine learning can greatly benefit from providing learning algorithms with pairs of contrastive training examples---typically pairs of instances that differ only slightly, yet have different class labels. Intuitively, the difference in the instances helps explain the difference in the class labels. This paper proposes a theoretical framework in which the effect of various types of contrastive examples on active learners is studied formally. The focus is on the sample complexity of learning concept classes and how it is influenced by the choice of contrastive examples. We illustrate our results with geometric concept classes and classes of Boolean functions. Interestingly, we reveal a connection between learning from contrastive examples and the classical model of self-directed learning.
BibTeX
@inproceedings{
mansouri2025formal,
title={Formal Models of Active Learning from Contrastive Examples},
author={Farnam Mansouri and Hans U. Simon and Adish Singla and Yuxin Chen and Sandra Zilles},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=AQ21krZgax}
}