This work proposes an adaptive semi-asynchronous federated learning (FL) approach, namely ASAFL, to incorporate the strengths of synchronous and asynchronous FL while mitigating their inherent drawbacks. Specifically, the edge server dynamically adjusts the synchronous degree, i.e., the number of local gradients aggregated in each round, to strike a balance between learning latency and accuracy. Recognizing that data heterogeneity among clients may induce biased global model updating, we propose calibrating the global update by leveraging historical gradients received at the edge server from clients. Following that, we experimentally revealed that allocating more learning time to the later learning stages to increase the synchronous degree contributes to better learning performance. Inspired by this, we develop an adaptive synchronous degree control and resource allocation algorithm to enhance the learning performance of FL while adhering to the overall learning latency and wireless resources constraint. Numerical results demonstrate that the proposed approach is capable of attaining faster convergence speed and higher learning accuracy compared to the benchmark FL algorithms.
Fast Wireless Federated Learning with Adaptive Synchronous Degree Control
24.06.2024
500214 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Fast converging Federated Learning with Non-IID Data
IEEE | 2023
|Partially synchronous federated learning vehicle re-identification method and system
Europäisches Patentamt | 2022
|ADAPTIVE ENVIRONMENTAL ADVERTISEMENT, USING FEDERATED LEARNING AND DRONES
Europäisches Patentamt | 2024
|