Federated Learning for Computationally-Constrained Heterogeneous Devices: A Survey

TL;DR

This survey reviews federated learning's challenges and solutions for deploying on heterogeneous, resource-constrained devices, emphasizing computation heterogeneity and recent adaptive approaches.

Contribution

It provides a comprehensive overview of heterogeneity-aware federated learning techniques, focusing on architecture adaptation and system-level solutions for real-world applications.

Findings

Heterogeneity significantly impacts federated learning effectiveness.

Recent methods include architecture adaptation and system-level approaches.

Asynchronous schemes improve training efficiency on diverse devices.

Abstract

With an increasing number of smart devices like internet of things (IoT) devices deployed in the field, offloadingtraining of neural networks (NNs) to a central server becomes more and more infeasible. Recent efforts toimprove users' privacy have led to on-device learning emerging as an alternative. However, a model trainedonly on a single device, using only local data, is unlikely to reach a high accuracy. Federated learning (FL)has been introduced as a solution, offering a privacy-preserving trade-off between communication overheadand model accuracy by sharing knowledge between devices but disclosing the devices' private data. Theapplicability and the benefit of applying baseline FL are, however, limited in many relevant use cases dueto the heterogeneity present in such environments. In this survey, we outline the heterogeneity challengesFL has to overcome to be widely applicable in real-world applications. We especially focus on the aspect ofcomputation heterogeneity among the participating devices and provide a comprehensive overview of recentworks on heterogeneity-aware FL. We discuss two groups: works that adapt the NN architecture and worksthat approach heterogeneity on a system level, covering Federated Averaging (FedAvg), distillation, and splitlearning-based approaches, as well as synchronous and asynchronous aggregation schemes.