Saved in:
Bibliographic Details
Main Authors: Lewis, Robert, Matton, Katie, Picard, Rosalind W., Guttag, John
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.07748
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918284147818496
author Lewis, Robert
Matton, Katie
Picard, Rosalind W.
Guttag, John
author_facet Lewis, Robert
Matton, Katie
Picard, Rosalind W.
Guttag, John
contents Self-supervised pre-training with contrastive learning is a powerful method for learning from sparsely labeled data. However, performance can drop considerably when there is a shift in the distribution of data from training to test time. We study this phenomenon in a setting in which the training data come from multiple domains, and the test data come from a domain not seen at training that is subject to significant covariate shift. We present a new method for contrastive learning that incorporates domain labels to increase the domain invariance of learned representations, leading to improved out-of-distribution generalization. Our method adjusts the temperature parameter in the InfoNCE loss -- which controls the relative weighting of negative pairs -- using the probability that a negative sample comes from the same domain as the anchor. This upweights pairs from more similar domains, encouraging the model to discriminate samples based on domain-invariant attributes. Through experiments on a variant of the MNIST dataset, we demonstrate that our method yields better out-of-distribution performance than domain generalization baselines. Furthermore, our method maintains strong in-distribution task performance, substantially outperforming baselines on this measure.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07748
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Improving Domain Generalization in Contrastive Learning using Adaptive Temperature Control
Lewis, Robert
Matton, Katie
Picard, Rosalind W.
Guttag, John
Machine Learning
Artificial Intelligence
Self-supervised pre-training with contrastive learning is a powerful method for learning from sparsely labeled data. However, performance can drop considerably when there is a shift in the distribution of data from training to test time. We study this phenomenon in a setting in which the training data come from multiple domains, and the test data come from a domain not seen at training that is subject to significant covariate shift. We present a new method for contrastive learning that incorporates domain labels to increase the domain invariance of learned representations, leading to improved out-of-distribution generalization. Our method adjusts the temperature parameter in the InfoNCE loss -- which controls the relative weighting of negative pairs -- using the probability that a negative sample comes from the same domain as the anchor. This upweights pairs from more similar domains, encouraging the model to discriminate samples based on domain-invariant attributes. Through experiments on a variant of the MNIST dataset, we demonstrate that our method yields better out-of-distribution performance than domain generalization baselines. Furthermore, our method maintains strong in-distribution task performance, substantially outperforming baselines on this measure.
title Improving Domain Generalization in Contrastive Learning using Adaptive Temperature Control
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.07748