FedPAGR: Federated Prototype Alignment via Geometric Refinement for Heterogeneous Architectures
Year: 2026
Type: conference-paper
Abstract: Federated learning with heterogeneous client architectures cannot rely on parameter aggregation.Prototype-based methods address architectural heterogeneity by exchanging classlevel representations, but naively averaging prototypes across non-IID clients leads to semantic drift and poor inter-class separation.We propose FedPAGR, a framework where heterogeneous clients project their features into a shared consensus space and exchange class prototypes with a central server.The server refines aggregated prototypes through a geometric regularization objective that enforces agreement with client submissions and inter-class angular separation.Clients anchor their classifiers to the refined prototypes and train with a composite objective combining classification, prototype alignment, and entropy regularization.We evaluate FedPAGR across multiple domains, including four image benchmarks and a clinical NLP task using heterogeneous ClinicalBERT variants, with five architectures per federation under severe label heterogeneity (α=0.1).Fed-PAGR achieves the highest ensemble accuracy across all four image datasets and the highest local test accuracy on low-class and clinical tasks, including a 4.99-point improvement over the strongest baseline on MIMIC-IV, while remaining competitive on high-class benchmarks.
Authors: Kris Prasad, Md Abdullah Al Hafiz Khan
Institution: Kennesaw State University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166854534