Graph Convolutional Mixture-of-Experts Learner Network for Long-Tailed Domain Generalization
Wang, Mengzhu Su, Houcheng Wang, Sijia Wang, Shanshan Yin, Nan Shen, Li Lan, Long Yang, Liang Cao, Xiachun
Wang, Mengzhu
Su, Houcheng
Wang, Sijia
Wang, Shanshan
Yin, Nan
Shen, Li
Lan, Long
Yang, Liang
Cao, Xiachun
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The goal of single domain generalization is to use data from a single domain (source domain) to train a model, which is then deployed over several unknown domains for testing (target domains). This study introduces a practical approach diverging from traditional DG, which typically relies on multiple source domains. We focus on Single Long-Tailed Domain Generalization, which refers to a scenario in the context of long-tail distribution, where although minority classes may have fewer samples in a single domain, these minority classes could become more prevalent and dominant in other domains. We introduce the Graph Convolutional Mixture-of-Experts Learners Network for Long-Tailed Domain Generalization (GCML) as a solution to this problem. Our approach presents two novel tactics. Initially, we utilize an expert learning technique that is skill-diverse. In order to properly manage the unknown target domain, this entails training multiple specialists inside a single long-tailed source domain and combining their knowledge. Then, we use a graph convolutional network to facilitate domain generalization, leveraging joint data structure modeling to learn more domain-invariant feature. Experiments conducted on four established benchmarks reveal that our GCML algorithm outperforms contemporary domain generalization techniques, demonstrating its efficacy in this complex task. © 2025 IEEE.
Citation
M. Wang et al., “Graph Convolutional Mixture-of-Experts Learner Network for Long-Tailed Domain Generalization,” IEEE Transactions on Circuits and Systems for Video Technology, 2025, doi: 10.1109/TCSVT.2025.3532309.
Source
IEEE Transactions on Circuits and Systems for Video Technology
Conference
Keywords
Data Structure, Domain Generalization, Domain-Invariant Feature, Mixture-of-Experts Learner
Subjects
Source
Publisher
IEEE