Qianjiao Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qianjiao Chen has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Baocheng Geng
University of Alabama at Birmingham
1 shared publication - 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 - Mengchen Fan
University of Alabama at Birmingham
1 shared publication - Roman Shterenberg
Department of Mathematics, The University of Alabama at Birmingham, Birmingham, AL, USA
1 shared publication - Zhong Chen
School of Computing, Southern Illinois University, Carbondale, USA
1 shared publication
Latest Publications
- 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.