Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection

2026-02-01

AI Summary

This work addresses the challenges of unstable convergence and degraded generalization in federated learning caused by non-IID data distributions. To this end, we propose FLood, a novel framework that, for the first time, integrates out-of-distribution (OOD) detection into federated learning. FLood introduces a plug-and-play dual-weighting mechanism: clients adaptively reweight the loss of pseudo-OOD samples based on OOD detection, while the server dynamically adjusts client aggregation weights according to their OOD confidence scores. Notably, FLood enhances the robustness, stability, and accuracy of the global model under heterogeneous data settings without requiring modifications to existing federated algorithms. Extensive experiments demonstrate that FLood consistently outperforms state-of-the-art methods across various non-IID scenarios.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes while preserving data privacy, making it a cornerstone of intelligent service systems in edge-cloud environments. However, in real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID. This severe data heterogeneity critically undermines the convergence stability, generalization ability, and ultimately the quality of service delivered by the global model. To address this challenge, we propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection. FLood dynamically counteracts the adverse effects of heterogeneity through a dual-weighting mechanism that jointly governs local training and global aggregation. At the client level, it adaptively reweights the supervised loss by upweighting pseudo-OOD samples, thereby encouraging more robust learning from distributionally misaligned or challenging data. At the server level, it refines model aggregation by weighting client contributions according to their OOD confidence scores, prioritizing updates from clients with higher in-distribution consistency and enhancing the global model's robustness and convergence stability. Extensive experiments across multiple benchmarks under diverse non-IID settings demonstrate that FLood consistently outperforms state-of-the-art FL methods in both accuracy and generalization. Furthermore, FLood functions as an orthogonal plug-in module: it seamlessly integrates with existing FL algorithms to boost their performance under heterogeneity without modifying their core optimization logic. These properties make FLood a practical and scalable solution for deploying reliable intelligent services in real-world federated environments.

Problem

• Federated Learning
• non-IID
• data heterogeneity
• out-of-distribution
• generalization

Innovation

• Federated Learning
• Out-of-Distribution Detection
• Dual-Weighting Mechanism
• Non-IID Data
• Robust Aggregation