Federated Learning with Energy-Based Structured Probabilistic Inference

Dario Fenoglio, Daniil Kirilenko, Martin Gjoreski, Marc Langheinrich

Keywords: federated learning, conditional random fields, structured inference, adaptive aggregation, non-IID data, client heterogeneity, robust aggregation, energy-based models

TL;DR: We formulate federated server aggregation as CRF-based structured inference, using client reliability and pairwise update compatibility to improve aggregation under non-IID heterogeneity.

Abstract: Federated learning typically aggregates client updates using fixed or heuristic weighting rules, which can be suboptimal when clients have heterogeneous data and varying contributions to the global model. We propose a framework that refines client aggregation weights using Conditional Random Fields (CRFs). Our method defines unary potentials for individual clients and pairwise potentials for all client pairs, allowing the server to model both client-specific reliability and interactions between clients. The resulting CRF inference produces aggregation weights that enable better convergence of the global training objective. Experiments show that, under non-IID heterogeneity, our approach consistently improves performance over well-established federated learning baselines.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 212