A Coopetitive-Compatible Data Generation Framework for Cross-silo Federated Learning
This addresses the problem of hesitant participation due to utility loss for organizations like hospitals or banks in federated learning, though it appears incremental by building on prior work on statistical heterogeneity.
The paper tackles the challenge of economic competition and statistical heterogeneity in cross-silo federated learning by proposing CoCoGen, a framework that uses generative AI and game theory to optimize collaborative learning, resulting in consistent outperformance over baseline methods on the Fashion-MNIST dataset.
Cross-silo federated learning (CFL) enables organizations (e.g., hospitals or banks) to collaboratively train artificial intelligence (AI) models while preserving data privacy by keeping data local. While prior work has primarily addressed statistical heterogeneity across organizations, a critical challenge arises from economic competition, where organizations may act as market rivals, making them hesitant to participate in joint training due to potential utility loss (i.e., reduced net benefit). Furthermore, the combined effects of statistical heterogeneity and inter-organizational competition on organizational behavior and system-wide social welfare remain underexplored. In this paper, we propose CoCoGen, a coopetitive-compatible data generation framework, leveraging generative AI (GenAI) and potential game theory to model, analyze, and optimize collaborative learning under heterogeneous and competitive settings. Specifically, CoCoGen characterizes competition and statistical heterogeneity through learning performance and utility-based formulations and models each training round as a weighted potential game. We then derive GenAI-based data generation strategies that maximize social welfare. Experimental results on the Fashion-MNIST dataset reveal how varying heterogeneity and competition levels affect organizational behavior and demonstrate that CoCoGen consistently outperforms baseline methods.