Problem
Research questions and friction points this paper is trying to address.
federated learning
personalization
generalization
Human Activity Recognition
FedAvg
FedAvg for HAR: Exploring the Tradeoff Between Personalized and Generalization Accuracy
🤖 AI Summary
This study addresses the trade-off between personalization and generalization in federated learning for human activity recognition, particularly under heterogeneous or dynamically shifting client data distributions. The authors construct a multi-scenario evaluation framework to systematically compare centralized, local, and federated learning (specifically FedAvg) under both standard and stress conditions, such as label distribution shifts. Experimental results demonstrate that FedAvg achieves superior personalization compared to centralized learning while maintaining strong generalization in conventional settings. However, this advantage markedly diminishes under severe distributional shifts, revealing critical limitations and defining the practical boundaries of FedAvg’s applicability in real-world deployments.
📝 Abstract
The federated learning (FL) paradigm fosters distributed pervasive computing combined with artificial intelligence techniques, allowing for optimized data usage and improved mitigation of privacy concerns. Indeed, model training occurs on the client's local devices, and model parameters are subsequently shared with a centralized server. However, there is a need to find a tradeoff between models' personalization and generalization capabilities. In this paper, we design and implement several testing scenarios devoted to evaluating and comparing the centralized, local, and federated paradigm performances. We also design and implement a scenario that emulates a change in clients' data. We then present experimental results of the FedAvg algorithm applied to the Human Activity Recognition (HAR) domain to understand the trade-off between personalized and generalized accuracy. Results show that, although FedAvg confirms a higher degree of personalization capabilities while keeping a high degree of generalization with respect to the traditional centralized learning, this result is not so obvious under stressful conditions, such as when varying class distribution over clients.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Federated Learning
FedAvg
Human Activity Recognition
Personalization-Generalization Tradeoff
Non-IID Data
🔎 Similar Papers
No similar papers found.
