Research map / Label-efficient and robust learning / Self-supervised and contrastive
Mitigating Spurious Features in Contrastive Learning with Spectral Regularization
Naghmeh Ghanooni, Waleed Mustafa, Dennis Wagner, Sophie Fellenz, Anthony Widjaja Lin, Marius Kloft
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a spectral regularization method to mitigate spurious features learned by contrastive self-supervised learning (abstract only; details unavailable).
Problem
Contrastive self-supervised representation learning is prone to learning simple spurious features correlated with labels, hurting performance on underrepresented classes or concepts and downstream tasks.
Approach
Identifies a key spectral property behind spurious feature learning in contrastive learning and mitigates it via spectral regularization; the abstract is truncated, so the specific mechanism is not stated.
Closest papers by meaning
- Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods (NeurIPS 2022 · similarity 0.89)
- Investigating Why Contrastive Learning Benefits Robustness against Label Noise (ICML 2022 · similarity 0.89)
- Towards the Generalization of Contrastive Self-Supervised Learning (ICLR 2023 · similarity 0.89)
- Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions (ICLR 2023 · similarity 0.88)
- Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning (NeurIPS 2025 · similarity 0.88)
- When Can We Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis? (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
