Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
This work addresses the problem of adapting federated learning models to new data silos with divergent distributions, offering a domain-specific solution that is incremental in nature.
The paper tackles the challenge of data heterogeneity in federated learning by proposing an uncertainty-based extensible codebook framework, which improves accuracy by 3% to 22.1% and reduces uncertainty by 38.83% to 96.24% across multiple datasets.
Federated learning (FL), aimed at leveraging vast distributed datasets, confronts a crucial challenge: the heterogeneity of data across different silos. While previous studies have explored discrete representations to enhance model generalization across minor distributional shifts, these approaches often struggle to adapt to new data silos with significantly divergent distributions. In response, we have identified that models derived from FL exhibit markedly increased uncertainty when applied to data silos with unfamiliar distributions. Consequently, we propose an innovative yet straightforward iterative framework, termed \emph{Uncertainty-Based Extensible-Codebook Federated Learning (UEFL)}. This framework dynamically maps latent features to trainable discrete vectors, assesses the uncertainty, and specifically extends the discretization dictionary or codebook for silos exhibiting high uncertainty. Our approach aims to simultaneously enhance accuracy and reduce uncertainty by explicitly addressing the diversity of data distributions, all while maintaining minimal computational overhead in environments characterized by heterogeneous data silos. Extensive experiments across multiple datasets demonstrate that UEFL outperforms state-of-the-art methods, achieving significant improvements in accuracy (by 3\%--22.1\%) and uncertainty reduction (by 38.83\%--96.24\%). The source code is available at https://github.com/destiny301/uefl.