A privacy-preserving, distributed and cooperative FCM-based learning approach for cancer research

TL;DR

The paper addresses privacy concerns in distributed learning for medical cancer detection by introducing a Federated Learning framework that trains PSO-based Fuzzy Cognitive Maps (FCMs) across multiple participants without sharing raw data. It formalizes a distributed FCM learning procedure, including PSO-based optimization of adjacency matrices and a privacy-preserving aggregation scheme that weights local models by accuracy. Experimental validation on the Breast Cancer Wisconsin dataset shows the approach achieves an average accuracy of 0.9383 after 20 iterations, with performance comparable to non-distributed methods reported in the literature. The work demonstrates a viable path for privacy-preserving distributed cancer diagnostics, enabling collaboration across institutions while complying with data privacy regulations.

Abstract

Distributed Artificial Intelligence is attracting interest day by day. In this paper, the authors introduce an innovative methodology for distributed learning of Particle Swarm Optimization-based Fuzzy Cognitive Maps in a privacy-preserving way. The authors design a training scheme for collaborative FCM learning that offers data privacy compliant with the current regulation. This method is applied to a cancer detection problem, proving that the performance of the model is improved by the Federated Learning process, and obtaining similar results to the ones that can be found in the literature.

Figures (3)

• Figure 1: Fuzzy Cognitive Maps classifier
• Figure 2: Federated Learning process
• Figure 3: Proposed methodology