Temporal-Structure-Assisted Gradient Aggregation for Over-the-Air Federated Edge Learning
This work addresses communication efficiency in federated edge learning, an incremental improvement for edge computing systems.
The paper tackles the problem of over-the-air model aggregation in federated edge learning by introducing a Markovian probability model to capture temporal structure, resulting in a message-passing algorithm (TSA-GA) that achieves near-optimal performance and comparable learning performance to an error-free benchmark in convergence rate and final test accuracy.
In this paper, we investigate over-the-air model aggregation in a federated edge learning (FEEL) system. We introduce a Markovian probability model to characterize the intrinsic temporal structure of the model aggregation series. With this temporal probability model, we formulate the model aggregation problem as to infer the desired aggregated update given all the past observations from a Bayesian perspective. We develop a message passing based algorithm, termed temporal-structure-assisted gradient aggregation (TSA-GA), to fulfil this estimation task with low complexity and near-optimal performance. We further establish the state evolution (SE) analysis to characterize the behaviour of the proposed TSA-GA algorithm, and derive an explicit bound of the expected loss reduction of the FEEL system under certain standard regularity conditions. In addition, we develop an expectation maximization (EM) strategy to learn the unknown parameters in the Markovian model. We show that the proposed TSAGA algorithm significantly outperforms the state-of-the-art, and is able to achieve comparable learning performance as the error-free benchmark in terms of both convergence rate and final test accuracy.