Joint Contrastive-Adversarial Representation Learning for Unsupervised Domain Adaptation

arXiv:2610.15613 · stat.ML, cs.LG · Submitted 2026-10-11 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-10-11

Updated: 2026-10-11

Comments: 29 pages, 5 figures, and 9 tables

Code: https://github.com/thuml/Transfer-Learning-Library

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adaptation — 1× in this paper · explained in 1 episode
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Representation Learning — 1× in this paper · explained in 3 episodes

Sources

• Domain-Adversarial Neural Networks
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Adaptation: Learning Bounds and Algorithms
• Deep Domain Confusion: Maximizing for Domain Invariance

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier