Moderately Distributional Exploration for Domain Generalization

Rui Dai, Yonggang Zhang*, Zhen Fang, Bo Han, Xinmei Tian*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

2 Citations (Scopus)

Abstract

Domain generalization (DG) aims to tackle the distribution shift between training domains and unknown target domains. Generating new domains is one of the most effective approaches, yet its performance gain depends on the distribution discrepancy between the generated and target domains. Distributionally robust optimization is promising to tackle distribution discrepancy by exploring domains in an uncertainty set. However, the uncertainty set may be overwhelmingly large, leading to low-confidence prediction in DG. It is because a large uncertainty set could introduce domains containing semantically different factors from training domains. To address this issue, we propose to perform a moderately distributional exploration (MODE) for domain generalization. Specifically, MODE performs distribution exploration in an uncertainty subset that shares the same semantic factors with the training domains. We show that MODE can endow models with provable generalization performance on unknown target domains. The experimental results show that MODE achieves competitive performance compared to state-of-the-art baselines.

Original languageEnglish
Title of host publicationProceedings of 40th International Conference on Machine Learning, ICML 2023
EditorsAndreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett
PublisherML Research Press
Pages6786-6817
Number of pages32
Publication statusPublished - Jul 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023
https://icml.cc/Conferences/2023
https://proceedings.mlr.press/v202/
https://openreview.net/group?id=ICML.cc/2023/Conference

Publication series

NameProceedings of Machine Learning Research
PublisherML Research Press
Volume202
ISSN (Print)2640-3498

Conference

Conference40th International Conference on Machine Learning, ICML 2023
Country/TerritoryUnited States
CityHonolulu
Period23/07/2329/07/23
Internet address

Scopus Subject Areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Moderately Distributional Exploration for Domain Generalization'. Together they form a unique fingerprint.

Cite this