Bayesian Neural Network For Personalized Federated Learning Parameter Selection
This addresses the problem of data heterogeneity in federated learning for clients needing personalized models, representing an incremental improvement over prior layer-level methods.
The paper tackles poor performance in federated learning with heterogeneous data by proposing personalized parameter selection at the elemental level using Bayesian neural networks, demonstrating that the approach outperforms existing baselines on real-world datasets.
Federated learning's poor performance in the presence of heterogeneous data remains one of the most pressing issues in the field. Personalized federated learning departs from the conventional paradigm in which all clients employ the same model, instead striving to discover an individualized model for each client to address the heterogeneity in the data. One of such approach involves personalizing specific layers of neural networks. However, prior endeavors have not provided a dependable rationale, and some have selected personalized layers that are entirely distinct and conflicting. In this work, we take a step further by proposing personalization at the elemental level, rather than the traditional layer-level personalization. To select personalized parameters, we introduce Bayesian neural networks and rely on the uncertainty they offer to guide our selection of personalized parameters. Finally, we validate our algorithm's efficacy on several real-world datasets, demonstrating that our proposed approach outperforms existing baselines.