Trans-XFed: An Explainable Federated Learning for Supply Chain Credit Assessment

TL;DR

Trans-XFed introduces an explainable federated learning framework for supply chain credit assessment, combining privacy-preserving techniques, client selection, and interpretability methods to improve accuracy and transparency in challenging data environments.

Contribution

It presents a novel federated learning architecture with explainability and a client selection strategy to address class imbalance, Non-IID data, and interpretability in supply chain credit assessment.

Findings

Achieves higher accuracy than baseline models.

Provides transparent decision explanations.

Maintains privacy with homomorphic encryption.

Abstract

This paper proposes a Trans-XFed architecture that combines federated learning with explainable AI techniques for supply chain credit assessment. The proposed model aims to address several key challenges, including privacy, information silos, class imbalance, non-identically and independently distributed (Non-IID) data, and model interpretability in supply chain credit assessment. We introduce a performance-based client selection strategy (PBCS) to tackle class imbalance and Non-IID problems. This strategy achieves faster convergence by selecting clients with higher local F1 scores. The FedProx architecture, enhanced with homomorphic encryption, is used as the core model, and further incorporates a transformer encoder. The transformer encoder block provides insights into the learned features. Additionally, we employ the integrated gradient explainable AI technique to offer insights into decision-making. We demonstrate the effectiveness of Trans-XFed through experimental evaluations on real-world supply chain datasets. The obtained results show its ability to deliver accurate credit assessments compared to several baselines, while maintaining transparency and privacy.