Adaptive Decentralized Federated Learning for Robust Optimization
This addresses robustness issues in decentralized federated learning for applications with noisy or poisoned data, though it appears incremental as it builds on existing methods with adaptive adjustments.
The paper tackles the problem of abnormal clients disrupting decentralized federated learning by proposing an adaptive method that adjusts client learning rates to mitigate negative impacts, achieving superior performance in experiments.
In decentralized federated learning (DFL), the presence of abnormal clients, often caused by noisy or poisoned data, can significantly disrupt the learning process and degrade the overall robustness of the model. Previous methods on this issue often require a sufficiently large number of normal neighboring clients or prior knowledge of reliable clients, which reduces the practical applicability of DFL. To address these limitations, we develop here a novel adaptive DFL (aDFL) approach for robust estimation. The key idea is to adaptively adjust the learning rates of clients. By assigning smaller rates to suspicious clients and larger rates to normal clients, aDFL mitigates the negative impact of abnormal clients on the global model in a fully adaptive way. Our theory does not put any stringent conditions on neighboring nodes and requires no prior knowledge. A rigorous convergence analysis is provided to guarantee the oracle property of aDFL. Extensive numerical experiments demonstrate the superior performance of the aDFL method.