Graph Federated Learning for CIoT Devices in Smart Home Applications

Abstract

This paper deals with the problem of statistical and system heterogeneity in a cross-silo Federated Learning (FL) framework where there exist a limited number of Consumer Internet of Things (CIoT) devices in a smart building. We propose a novel Graph Signal Processing (GSP)-inspired aggregation rule based on graph filtering dubbed ``G-Fedfilt''. The proposed aggregator enables a structured flow of information based on the graph's topology. This behavior allows capturing the interconnection of CIoT devices and training domain-specific models. The embedded graph filter is equipped with a tunable parameter which enables a continuous trade-off between domain-agnostic and domain-specific FL. In the case of domain-agnostic, it forces G-Fedfilt to act similar to the conventional Federated Averaging (FedAvg) aggregation rule. The proposed G-Fedfilt also enables an intrinsic smooth clustering based on the graph connectivity without explicitly specified which further boosts the personalization of the models in the framework. In addition, the proposed scheme enjoys a communication-efficient time-scheduling to alleviate the system heterogeneity. This is accomplished by adaptively adjusting the amount of training data samples and sparsity of the models' gradients to reduce communication desynchronization and latency. Simulation results show that the proposed G-Fedfilt achieves up to $3.99\%$ better classification accuracy than the conventional FedAvg when concerning model personalization on the statistically heterogeneous local datasets, while it is capable of yielding up to $2.41\%$ higher accuracy than FedAvg in the case of testing the generalization of the models.

arXiv commentThe GitHub code: https://github.com/FL-HAR/Graph-Federated-Learning-for-CIoT-Devices.git, Published in IEEE Internet of Things Journal

References in corpus (19)

• Federated Learning: Challenges, Methods, and Future Directions
• Dynamic Computation Offloading for Mobile-Edge Computing with Energy Harvesting Devices
• Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
• Towards Personalized Federated Learning
• On the Convergence of FedAvg on Non-IID Data
• Sparse Communication for Distributed Gradient Descent
• Federated Learning with Personalization Layers
• Improving Federated Learning Personalization via Model Agnostic Meta Learning
• Personalized Federated Learning: A Meta-Learning Approach
• Fair Resource Allocation in Federated Learning
• Adaptive Personalized Federated Learning
• Three Approaches for Personalization with Applications to Federated Learning
• Graph signal processing for machine learning: A review and new perspectives
• Federated Learning: A Signal Processing Perspective
• Variational Federated Multi-Task Learning
• FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
• GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs
• FLeet: Online Federated Learning via Staleness Awareness and Performance Prediction
• Federated Dynamic GNN with Secure Aggregation

Cited by in corpus (2)

• A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks
• Decentralized Proactive Model Offloading and Resource Allocation for Split and Federated Learning