Yuxuan Luan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuxuan Luan has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Haipeng Peng
Beijing University of Posts and Telecommunications
4 shared publications - Lixiang Li
Beijing University of Posts and Telecommunications
4 shared publications - Zilin Zhao
Beijing University of Posts and Telecommunications
3 shared publications - Wei Wang
Institute for Advanced Study, Tsinghua University, Beijing, China
2 shared publications - Chaoning Zhang
University of Electronic Science and Technology of China, Chengdu, Sichuan, China
1 shared publication Jiashuo Song
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15521-15529
FedSA-OV: Preserving Cross-Modal Semantics for Heterogeneous Federated Open-Vocabulary Learning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15521-15529
Open AccessFedSA-OV: Preserving Cross-Modal Semantics for Heterogeneous Federated Open-Vocabulary Learning
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7273-7282
FedGAT: Federated Geometry-Aware and Topological Condensation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7273-7282
Open AccessFedGAT: Federated Geometry-Aware and Topological Condensation
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47463-47481
Fed-FIDES: A Unified Framework for Robust and Personalized Federated Learning in Resource-Constrained IoT
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47463-47481
Fed-FIDES: A Unified Framework for Robust and Personalized Federated Learning in Resource-Constrained IoT
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (6) , 12105-12118
Personalized Federated Learning With Multigranularity Confidence Alignment for IoT Device Collaboration
Federated learning (FL) provides a privacy-preserving solution for model training across distributed Internet of Things (IoT) devices. IoT scenarios typically involve highly heterogeneous data, limited computational capacity, and unstable communication links. Non-independent and identically distributed (non-IID) data further exacerbate training difficulties. Common challenges include reduced model generalization, insufficient robustness against abnormal inputs, and performance unfairness among clients. To address these challenges, personalized federated learning with multi-granularity confidence alignment (FedMGCA) is introduced. FedMGCA incorporates a multi-granularity confidence alignment mechanism to calibrate model confidence at the feature, decision, and distribution levels. In addition, a trust-based dynamic aggregation strategy is adopted to reweight client updates based on reliability assessments. The experimental results demonstrate that FedMGCA consistently outperforms existing personalized federated learning algorithms across various benchmarks.
- 15 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (6) , 12105-12118
Personalized Federated Learning With Multigranularity Confidence Alignment for IoT Device Collaboration
Federated learning (FL) provides a privacy-preserving solution for model training across distributed Internet of Things (IoT) devices. IoT scenarios typically involve highly heterogeneous data, limited computational capacity, and unstable communication links. Non-independent and identically distributed (non-IID) data further exacerbate training difficulties. Common challenges include reduced model generalization, insufficient robustness against abnormal inputs, and performance unfairness among clients. To address these challenges, personalized federated learning with multi-granularity confidence alignment (FedMGCA) is introduced. FedMGCA incorporates a multi-granularity confidence alignment mechanism to calibrate model confidence at the feature, decision, and distribution levels. In addition, a trust-based dynamic aggregation strategy is adopted to reweight client updates based on reliability assessments. The experimental results demonstrate that FedMGCA consistently outperforms existing personalized federated learning algorithms across various benchmarks.