Portrait de Changjian Shui n'est pas disponible

Changjian Shui

Alumni

Publications

Evolving Domain Generalization
Wei Wang
Gezheng Xu
Ruizhi Pu
Jiaqi Li
Fan Zhou
Charles Ling
Boyu Wang
On the benefits of representation regularization in invariance based domain generalization
A crucial aspect of reliable machine learning is to design a deployable system for generalizing new related but unobserved environments. Dom… (voir plus)ain generalization aims to alleviate such a prediction gap between the observed and unseen environments. Previous approaches commonly incorporated learning the invariant representation for achieving good empirical performance. In this paper, we reveal that merely learning the invariant representation is vulnerable to the related unseen environment. To this end, we derive a novel theoretical analysis to control the unseen test environment error in the representation learning, which highlights the importance of controlling the smoothness of representation. In practice, our analysis further inspires an efficient regularization method to improve the robustness in domain generalization. The proposed regularization is orthogonal to and can be straightforwardly adopted in existing domain generalization algorithms that ensure invariant representation learning. Empirical results show that our algorithm outperforms the base versions in various datasets and invariance criteria.
Deep Active Learning: Unified and Principled Method for Query and Training
Fan Zhou
Boyu Wang