Adversarial data splitting for domain generalization

Xiang GU ¹Jian SUN ¹Zongben XU¹

扫码查看

作者信息

1. School of Mathematics and Statistics,Xi'an Jiaotong University,Xi'an 710049,China
折叠

Abstract

Domain generalization aims to learn a model that is generalizable to an unseen target domain,which is a fundamental and challenging task in machine learning for out-of-distribution generalization.This paper proposes a novel domain generalization approach that enforces the learned model to be able to gen-eralize well over the train/val subset splitting of the training dataset.This idea is modeled herein as an adversarial data splitting framework,formulated as a min-max optimization problem inspired by the meta-learning approach.The min-max optimization problem is solved by iteratively splitting the training dataset into the training and val subsets to maximize the domain shift measured by the objective function and updating the model parameters to enable the model to generalize well from the training subset to the val subset by minimizing the objective function.This adversarial training approach does not assume the known domain labels of the training data;instead,it automatically investigates the"hard"splitting of the train/val subsets to learn the generalizable model.Extensive experimental results using three benchmark datasets demonstrate the superiority of this approach.In addition,we derive a generalization error bound for the theoretical understanding of our proposed approach.

Key words

domain generalization/adversarial learning/data splitting/meta-learning/out of distribution

引用本文复制引用

基金项目

National Key R&D Program of China(2021YFA1003002)

National Natural Science Foundation of China(U20B2075)

National Natural Science Foundation of China(12125104)

National Natural Science Foundation of China(11971373)

National Natural Science Foundation of China(61721002)

Fundamental Research Funds for the Central Universities()

出版年

2024

中国科学:信息科学(英文版)

中国科学院

中国科学:信息科学(英文版)

CSTPCDEI

影响因子：0.715

ISSN：1674-733X

参考文献量64

段落导航