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

2025-08-19

AI Summary

To address critical challenges in supply chain credit assessment—including privacy preservation, data silos, class imbalance, non-IID data distribution, and model interpretability—this paper proposes Trans-XFed, a novel distributed credit evaluation framework integrating federated learning with explainable AI. Methodologically, it introduces a performance-aware client selection strategy to accelerate convergence under non-IID conditions; employs a Transformer encoder to model heterogeneous temporal credit features; ensures secure aggregation via homomorphic encryption and FedProx; and incorporates integrated gradients for fine-grained feature attribution, enhancing decision transparency. Experimental evaluation on a real-world supply chain dataset demonstrates that Trans-XFed significantly outperforms multiple baseline models in accuracy, while simultaneously achieving strong privacy guarantees, high robustness to data heterogeneity, and intrinsic model interpretability.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Addressing privacy and data silos in supply chain credit assessment
• Solving class imbalance and Non-IID data distribution challenges
• Enhancing model interpretability while maintaining federated learning security

Innovation

• Federated learning with explainable AI
• Client selection strategy for faster convergence
• Homomorphic encryption and transformer encoder