Fangbin Xu

Fangbin Xu

Auto-generated profile, based on publicly available information

Fangbin Xu

College of Information Science and Engineering, Northeastern University, Shenyang, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 May 2024 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
FXFangbin Xu
Fangbin Xu
DCDongyue Chen
Dongyue Chen
TJTong Jia
Tong Jia
SDShizhuo Deng
Shizhuo Deng
HWHao Wang
Hao Wang
Machine learning models often suffer from severe performance degradation due to distributional shifts between testing and training data. To address this issue, researchers have focused on domain generalization (DG), which aims to generalize a model trained on source domains to arbitrary unseen target domains. Recently, ensemble learning has emerged as a popular strategy for addressing the DG problem, and domain-specific experts are typically involved. However, the existing methods do not sufficiently consider the generalizability of individual experts or leverage the consistency and diversity among them, thus limiting the generalizability of the constructed models. In this paper, we propose a consistent-but-diverse mixture of experts (CBDMoE) algorithm, which is an improved MoE framework that effectively harnesses ensemble learning for solving the DG problem. Specifically, we introduce individual expert learning (IEL), which incorporates a novel domain-class-balanced subset division (DCBSD)-based sampling strategy to facilitate a generalizable expert learning process. Additionally, we present consistent-but-diverse learning (CBDL), which employs two regularizing losses to encourage consistency and diversity in the predictions of the experts. Our proposed strategy significantly enhances the generalizability of the MoE framework. Extensive experiments conducted on three popular DG benchmark datasets demonstrate that our method outperforms the state-of-the-art approaches.

8 August 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
FXFangbin Xu
Fangbin Xu
SDShizhuo Deng
Shizhuo Deng
TJTong Jia
Tong Jia
XYXiaosheng Yu
Xiaosheng Yu
DCDongyue Chen
Dongyue Chen