Distributed Collaborative Learning with Representative Knowledge Sharing
Joseph Casey, Qianjiao Chen, Mengchen Fan, Baocheng Geng, Roman Shterenberg, Zhong Chen, Keren Li
Source abstract
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.
Evidence graph
No public relationships recorded yet.
Integrity note: This page is a factual metadata record created by deterministic ingestion. It is not a claim that the work moves a mathematical frontier or has been independently verified.