stat.MLNov 13, 2026

Contrastive latent representation learning with denoising score matching

Authors: Christopher Marouani, Grigory Bartosh, Christian A. Naesseth

Organizations: ENS Paris-Saclay · University of Amsterdam

Abstract

Contrastive representation learning methods operate by pulling different views of the same data sample together while pushing them away from views of different samples. A fundamental challenge is the estimation of the repulsive force, which typically requires large batch sizes, can exhibit high variance, and is susceptible to the curse of dimensionality. We introduce ScoreCLR, a contrastive representation learning method that offers a novel way to estimate this repulsion term. We consider the framework of representation learning by maximizing the mutual information between two latent views of a sample. By deriving the gradient of the Shannon entropy with respect to the encoder parameters, we obtain an equivalent objective that involves the score of the latent representation. We then use denoising score matching techniques to estimate this score with a lightweight network that is trained jointly with the encoder. We further propose regularization techniques using different noise levels and a Gaussian prior on the latent representation. ScoreCLR replaces the batch of explicit negative samples in contrastive methods with a learned repulsion whose cost is linear in the batch size rather than quadratic. On CIFAR-10 and ImageNet-100 it does so with minimal loss of linear-probe accuracy compared to SimCLR under a shared recipe, while producing projector outputs of higher effective rank, closer to the Gaussian prior.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Approximation in Contrastive Representation Learning

    Oct 11, 2026Yuanfan Li, Zihan Zhang, Yiming Ying +1Contrastive LearningMultimodal Contrastive Learning

  2. Bayesian Gated Non-Negative Contrastive Learning

    May 27, 2026Peng Cui, Jiahao Zhang, Lijie HuContrastive LearningDisentangled Representation Learning

  3. The Loss Is Not Enough: Sampling Conditions and Inductive Bias in Contrastive Representation Learning

    Jun 2, 2026Justinas Zaliaduonis, Patrick Putzky, Till Richter +1Contrastive LearningSelf-Supervised Learning