Keywords: self-supervised contrastive learning, sufficient dimension reduction, Fisher discriminant analysis
TL;DR: We propose Fisher Contrastive Learning (FCL), which addresses the feature suppression effect in self-supervised learning by estimating the sufficient dimension reduction function class, preserving key features and outperforming existing benchmarks.
Abstract: Self-supervised contrastive learning (SSCL) is a rapidly advancing approach for learning data representations. However, a significant challenge in this paradigm is the feature suppression effect, where useful features for downstream tasks are suppressed due to dominant or easy-to-learn features overshadowing others crucial for downstream performance, ultimately degrading the performance of SSCL models. While prior research has acknowledged the feature suppression effect, solutions with theoretical guarantees to mitigate this issue are still lacking. In this work, we address the feature suppression problem by proposing a novel method, Fisher Contrastive Learning, which unbiasedly and exhaustively estimates the central sufficient dimension reduction function class in SSCL settings. In addition, FCL empirically maintains the embedding dimensionality by maximizing the discriminative power of each linear classifier learned through Fisher Contrastive Learning. We demonstrate that using our proposed method, the class-relevant features are not suppressed by strong or easy-to-learn features on datasets known for strong feature suppression effects. In addition, the embedding dimensionality is not preserved in practice. Furthermore, we show that Fisher Contrastive Learning consistently outperforms existing benchmark methods on standard image benchmarks, illustrating its practical advantages.
Supplementary Material: zip
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13107
Loading