FedTeddi: Temporal Drift and Divergence Aware Scheduling for Timely Federated Edge Learning

2025-09-08

AI Summary

To address model update lag in federated edge learning (FEEL) caused by dynamic non-i.i.d. data streams, this paper proposes an adaptive client scheduling framework tailored for time-varying data. We introduce a novel dual-dimensional quantification mechanism—capturing both temporal drift and collective divergence—and pioneer the use of Earth Mover’s Distance (EMD) to model class-level distribution shifts. A joint optimization objective is designed to balance knowledge transfer and catastrophic forgetting mitigation. Furthermore, we integrate dynamic client scheduling with bandwidth-aware resource allocation to accelerate global model convergence. Experiments on CIFAR-10 and CIFAR-100 demonstrate that our method achieves 58.4% and 49.2% faster convergence, respectively, compared to random scheduling, while significantly improving final test accuracy. Key contributions include: (i) the first EMD-based characterization of class-level non-i.i.d. dynamics in FEEL; (ii) a unified framework jointly optimizing scheduling, resource allocation, and model adaptation under temporal distribution shifts; and (iii) empirical validation of substantial gains in both convergence speed and generalization performance.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Federated edge learning (FEEL) enables collaborative model training across distributed clients over wireless networks without exposing raw data. While most existing studies assume static datasets, in real-world scenarios clients may continuously collect data with time-varying and non-independent and identically distributed (non-i.i.d.) characteristics. A critical challenge is how to adapt models in a timely yet efficient manner to such evolving data. In this paper, we propose FedTeddi, a temporal-drift-and-divergence-aware scheduling algorithm that facilitates fast convergence of FEEL under dynamic data evolution and communication resource limits. We first quantify the temporal dynamics and non-i.i.d. characteristics of data using temporal drift and collective divergence, respectively, and represent them as the Earth Mover's Distance (EMD) of class distributions for classification tasks. We then propose a novel optimization objective and develop a joint scheduling and bandwidth allocation algorithm, enabling the FEEL system to learn from new data quickly without forgetting previous knowledge. Experimental results show that our algorithm achieves higher test accuracy and faster convergence compared to benchmark methods, improving the rate of convergence by 58.4% on CIFAR-10 and 49.2% on CIFAR-100 compared to random scheduling.

Problem

• Addresses temporal drift and non-iID data in federated edge learning
• Optimizes client scheduling and bandwidth allocation for faster convergence
• Maintains model accuracy while adapting to evolving data streams

Innovation

• Temporal drift and divergence aware scheduling
• Joint scheduling and bandwidth allocation algorithm
• Earth Mover's Distance for class distribution quantification