Robust Federated Learning with Global Sensitivity Estimation for Financial Risk Management

2025-02-24

AI Summary

Federated learning (FL) in decentralized finance (DeFi) suffers from unstable training and insufficient resilience to systemic risks under client heterogeneity. Method: We propose FRAL-CSE, a robust FL framework featuring (i) a novel center-acceleration mechanism grounded in global sensitivity estimation, coupled with curvature-aware second-order sensitivity approximation for parameter updates; and (ii) the first integration of distorted risk measures into the FL objective, enabling explicit tail-risk modeling. Contribution/Results: Evaluated on heterogeneous financial datasets, FRAL-CSE significantly improves convergence speed and robustness under extreme scenarios—outperforming all existing state-of-the-art methods. It establishes a verifiable, risk-aware FL paradigm for trustworthy collaborative modeling in DeFi, advancing both theoretical rigor and practical deployability.

Technology Category

Machine Learning: Distributed Machine Learning & Federated LearningNatural Language Processing: Safety and RobustnessMultiagent Systems: Mechanism Design

Application Category

User Modeling, Personalization and Recommendation: Federated recommendation systems and personalizationSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingResponsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In decentralized financial systems, robust and efficient Federated Learning (FL) is promising to handle diverse client environments and ensure resilience to systemic risks. We propose Federated Risk-Aware Learning with Central Sensitivity Estimation (FRAL-CSE), an innovative FL framework designed to enhance scalability, stability, and robustness in collaborative financial decision-making. The framework's core innovation lies in a central acceleration mechanism, guided by a quadratic sensitivity-based approximation of global model dynamics. By leveraging local sensitivity information derived from robust risk measurements, FRAL-CSE performs a curvature-informed global update that efficiently incorporates second-order information without requiring repeated local re-evaluations, thereby enhancing training efficiency and improving optimization stability. Additionally, distortion risk measures are embedded into the training objectives to capture tail risks and ensure robustness against extreme scenarios. Extensive experiments validate the effectiveness of FRAL-CSE in accelerating convergence and improving resilience across heterogeneous datasets compared to state-of-the-art baselines.

Problem

• Enhancing robust Federated Learning
• Central Sensitivity Estimation for stability
• Financial risk management in decentralized systems

Innovation

• Federated Learning framework
• quadratic sensitivity-based approximation
• distortion risk measures