The Two Dimensions of Worst-case Training and Their Integrated Effect for Out-of-domain Generalization

Zeyi Huang, Haohan Wang, Dong Huang, Yong Jae Lee, Eric P. Xing

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Training with an emphasis on 'hard-to-learn' components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e.g., generalization across distributions) is valued. Existing literature discussing this 'hard-to-learn' concept are mainly expanded either along the dimension of the samples or the dimension of the features. In this paper, we aim to introduce a simple view merging these two dimensions, leading to a new, simple yet effective, heuristic to train machine learning models by emphasizing the worst-cases on both the sample and the feature dimensions. We name our method W2D following the concept of 'Worst-case along Two Dimensions'. We validate the idea and demonstrate its empirical strength over standard benchmarks.

Original languageEnglish (US)
Title of host publicationProceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
PublisherIEEE Computer Society
Pages9621-9631
Number of pages11
ISBN (Electronic)9781665469463
DOIs
StatePublished - 2022
Externally publishedYes
Event2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, United States
Duration: Jun 19 2022Jun 24 2022

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2022-June
ISSN (Print)1063-6919

Conference

Conference2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
Country/TerritoryUnited States
CityNew Orleans
Period6/19/226/24/22

Keywords

  • Self-& semi-& meta- Representation learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'The Two Dimensions of Worst-case Training and Their Integrated Effect for Out-of-domain Generalization'. Together they form a unique fingerprint.

Cite this