A Fair Federated Learning Framework for Collaborative Network Traffic Prediction and Resource Allocation

2025-02-10

AI Summary

Addressing dual challenges of privacy preservation and fairness in multi-operator collaborative traffic forecasting and resource allocation for B5G digital twin networks, this paper proposes the first federated learning framework that explicitly quantifies fairness—via coefficient of variation (CV) of prediction accuracy—as an integral component of the learning objective. Methodologically, it integrates Non-IID and class-imbalanced data modeling, realistic elastic optical network traffic simulation, and sensitive-attribute-aware fair regularization. Its key innovation lies in jointly ensuring fairness in both cross-operator model contribution and connection-level QoS allocation. Experiments on real optical network trajectory data demonstrate a 42% reduction in prediction accuracy disparity (CV), a 37% improvement in QoS allocation fairness, and empirically validate the efficacy of prediction fairness as a driver for fair resource allocation.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Learning & Optimization for CV
• Game Theory and Economic Paradigms: Fair Division

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

In the beyond 5G era, AI/ML empowered realworld digital twins (DTs) will enable diverse network operators to collaboratively optimize their networks, ultimately improving end-user experience. Although centralized AI-based learning techniques have been shown to achieve significant network traffic accuracy, resulting in efficient network operations, they require sharing of sensitive data among operators, leading to privacy and security concerns. Distributed learning, and specifically federated learning (FL), that keeps data isolated at local clients, has emerged as an effective and promising solution for mitigating such concerns. Federated learning poses, however, new challenges in ensuring fairness both in terms of collaborative training contributions from heterogeneous data and in mitigating bias in model predictions with respect to sensitive attributes. To address these challenges, a fair FL framework is proposed for collaborative network traffic prediction and resource allocation. To demonstrate the effectiveness of the proposed approach, noniid and imbalanced federated datasets based on real-word traffic traces are utilized for an elastic optical network. The assumption is that different optical nodes may be managed by different operators. Fairness is evaluated according to the coefficient of variations measure in terms of accuracy across the operators and in terms of quality-of-service across the connections (i.e., reflecting end-user experience). It is shown that fair traffic prediction across the operators result in fairer resource allocations across the connections.

Problem

• Ensuring fairness in federated learning
• Mitigating bias in model predictions
• Optimizing network resource allocation

Innovation

• Federated Learning Framework
• Collaborative Network Optimization
• Fair Resource Allocation