Federated Learning for Computationally-Constrained Heterogeneous Devices: A Survey
It tackles the problem of making federated learning more practical for real-world applications with diverse device capabilities, but it is incremental as it surveys existing works rather than introducing new methods.
This survey addresses the challenge of applying federated learning to environments with computationally heterogeneous devices, such as IoT, by outlining the limitations of baseline FL and providing an overview of recent heterogeneity-aware approaches, including NN architecture adaptations and system-level methods like FedAvg, distillation, and split learning.
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.