Towards Explainable Multi-Party Learning: A Contrastive Knowledge Sharing Framework

TL;DR

This paper introduces a contrastive multi-party learning framework that enhances knowledge sharing and model performance while addressing heterogeneity and incentive challenges in decentralized data environments.

Contribution

It proposes a novel contrastive learning approach that simulates human cognition for transparent knowledge sharing without privacy risks, improving multi-party learning efficiency.

Findings

Significant performance improvements across multiple datasets

Effective handling of system and statistical heterogeneity

Robust incentive mechanism for participant engagement

Abstract

Multi-party learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multi-party learning approaches are confronted with obstacles such as system heterogeneity, statistical heterogeneity, and incentive design. How to deal with these challenges and further improve the efficiency and performance of multi-party learning has become an urgent problem to be solved. In this paper, we propose a novel contrastive multi-party learning framework for knowledge refinement and sharing with an accountable incentive mechanism. Since the existing naive model parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication, and analogy multi-party learning as a many-to-one knowledge sharing problem. The approach is capable of integrating the acquired explicit knowledge of each client in a transparent manner without privacy disclosure, and it reduces the dependence on data distribution and communication environments. The proposed scheme achieves significant improvement in model performance in a variety of scenarios, as we demonstrated through experiments on several real-world datasets.