Mengchen Fan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mengchen Fan has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Baocheng Geng
University of Alabama at Birmingham
2 shared publications - Joseph Casey
Department of Mathematics, University of Alabama at Birmingham, Birmingham, AL 35294, USA
1 shared publication - Keren Li
Department of Mathematics, University of Alabama at Birmingham, Birmingham, AL 35294, USA
1 shared publication - Pulin Che
Department of Anesthesiology and Perioperative Medicine, Division of Molecular and Translational Biomedicine, University of Alabama at Birmingham, Birmingham, AL 35294, USA
1 shared publication - Qianjiao Chen
Department of Mathematics, University of Alabama at Birmingham, Birmingham, AL 35294, USA
1 shared publication - Qizhen Lan
UThealth houston
1 shared publication
Latest Publications
- 27 September 2026
- Published by Springer Nature
- p. 123-133
Detail Consistent Stage-Wise Distillation for Efficient 3D MRI Segmentation
- 27 September 2026
- Published by Springer Nature
- p. 123-133
Detail Consistent Stage-Wise Distillation for Efficient 3D MRI Segmentation
- Open Access
- 19 March 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (6) , 1004
Distributed Collaborative Learning with Representative Knowledge Sharing
Distributed Collaborative Learning (DCL) addresses critical challenges in privacy-aware machine learning by enabling indirect knowledge transfer across nodes with heterogeneous feature distributions. Unlike conventional federated learning approaches, DCL assumes non-IID data and prediction task distributions that span beyond local training data, requiring selective collaboration to achieve generalization. In this work, we propose a novel collaborative transfer learning (CTL) framework that utilizes representative datasets and adaptive distillation weights to facilitate efficient and privacy-preserving collaboration. By leveraging Energy Coefficients to quantify node similarity, CTL dynamically selects optimal collaborators and refines local models through knowledge distillation on shared representative datasets. Simulations demonstrate the efficacy of CTL in improving prediction accuracy across diverse tasks while balancing trade-offs between local and global performance. Furthermore, we explore the impact of data spread and dispersion on collaboration, highlighting the importance of tailored node alignment. This framework provides a scalable foundation for cross-domain generalization in distributed machine learning.
- 19 March 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (6) , 1004
Open AccessDistributed Collaborative Learning with Representative Knowledge Sharing
Distributed Collaborative Learning (DCL) addresses critical challenges in privacy-aware machine learning by enabling indirect knowledge transfer across nodes with heterogeneous feature distributions. Unlike conventional federated learning approaches, DCL assumes non-IID data and prediction task distributions that span beyond local training data, requiring selective collaboration to achieve generalization. In this work, we propose a novel collaborative transfer learning (CTL) framework that utilizes representative datasets and adaptive distillation weights to facilitate efficient and privacy-preserving collaboration. By leveraging Energy Coefficients to quantify node similarity, CTL dynamically selects optimal collaborators and refines local models through knowledge distillation on shared representative datasets. Simulations demonstrate the efficacy of CTL in improving prediction accuracy across diverse tasks while balancing trade-offs between local and global performance. Furthermore, we explore the impact of data spread and dispersion on collaboration, highlighting the importance of tailored node alignment. This framework provides a scalable foundation for cross-domain generalization in distributed machine learning.