Attentive Federated Learning for Concept Drift in Distributed 5G Edge Networks

TL;DR

This paper proposes an attention-based federated learning approach to effectively handle concept drift in distributed 5G edge networks, improving model accuracy amid changing data distributions.

Contribution

It introduces an attention mechanism within federated learning to better adapt to concept drift in heterogeneous 5G edge environments, a novel approach for continual learning.

Findings

Attention improves concept drift detection in federated learning.

The method achieves lower error rates during distribution shifts.

Enhanced adaptability in 5G network traffic scenarios.

Abstract

Machine learning (ML) is expected to play a major role in 5G edge computing. Various studies have demonstrated that ML is highly suitable for optimizing edge computing systems as rapid mobility and application-induced changes occur at the edge. For ML to provide the best solutions, it is important to continually train the ML models to include the changing scenarios. The sudden changes in data distributions caused by changing scenarios (e.g., 5G base station failures) is referred to as concept drift and is a major challenge to continual learning. The ML models can present high error rates while the drifts take place and the errors decrease only after the model learns the distributions. This problem is more pronounced in a distributed setting where multiple ML models are being used for different heterogeneous datasets and the final model needs to capture all concept drifts. In this paper, we show that using Attention in Federated Learning (FL) is an efficient way of handling concept drifts. We use a 5G network traffic dataset to simulate concept drift and test various scenarios. The results indicate that Attention can significantly improve the concept drift handling capability of FL.