DOMAIN GENERALIZATION VIA PARETO OPTIMAL GRADIENT MATCHING

27 Sept 2024 (modified: 05 Feb 2025)Submitted to ICLR 2025EveryoneRevisionsBibTeXCC BY 4.0
Keywords: Domain Generalization
TL;DR: Rethinking Fish, Fishr and improve with new algorithm
Abstract:

In this study, we address the gradient-based domain generalization problem, where predictors aim for consistent gradient directions across different domains. Existing methods have two main challenges. First, minimization of gradient empirical distance or gradient inner products (GIP) leads to gradient fluctuations and magnitude elimination among domains, thereby hindering straightforward learning. Second, the direct application of gradient learning to joint loss function can incur high computation overheads due to second-order derivative approximation. To tackle these challenges, we propose a new Pareto Optimality Gradient Matching (POGM) method. In contrast to existing methods that add gradient matching as regularization, we leverage gradient trajectories as collected data and apply independent training at the meta-learner. In the meta-update, we maximize GIP while limiting the learned gradient from deviating too far from the empirical risk minimization gradient trajectory. By doing so, the aggregate gradient can incorporate knowledge from all domains without suffering gradient magnitude elimination or fluctuation towards any particular domain. Experimental evaluations on datasets from DomainBed demonstrate competitive results yielded by POGM against other baselines while achieving computational efficiency.

Supplementary Material: zip
Primary Area: transfer learning, meta learning, and lifelong 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.
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: 9086
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview