Personalized Federated Learning under Model Dissimilarity Constraints
This addresses the problem of statistical heterogeneity for federated learning clients, offering an incremental improvement over existing methods like clustered approaches.
The paper tackles statistical heterogeneity in federated learning by introducing KARULA, a personalized federated learning strategy that constrains model dissimilarities based on distribution differences, and demonstrates its effectiveness on synthetic and real datasets with a convergence rate of O(1/K).
One of the defining challenges in federated learning is that of statistical heterogeneity among clients. We address this problem with KARULA, a regularized strategy for personalized federated learning, which constrains the pairwise model dissimilarities between clients based on the difference in their distributions, as measured by a surrogate for the 1-Wasserstein distance adapted for the federated setting. This allows the strategy to adapt to highly complex interrelations between clients, that e.g., clustered approaches fail to capture. We propose an inexact projected stochastic gradient algorithm to solve the constrained problem that the strategy defines, and show theoretically that it converges with smooth, possibly non-convex losses to a neighborhood of a stationary point with rate O(1/K). We demonstrate the effectiveness of KARULA on synthetic and real federated data sets.