FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet

arXiv:2604.22494v1 Announce Type: cross Abstract: We introduce two federated learning frameworks for the classical SPDnet model operating on symmetric positive definite (SPD) matrices with Stiefel-constrained parameters. Unlike standard Euclidean averaging, which violates orthogonality, our approach preserves geometric structure through two efficient aggregation strategies: ProjAvg, projecting arithmetic means onto the Stiefel manifold, and RLAvg, approximating tangent-space averaging via retractions and liftings. Both methods are computationally efficient, independent of the optimizer, and enable scalable federated learning for signal processing applications whose features are SPD matrices. Simulations on EEG motor imagery benchmarks show that FedSPDnet outperforms federated EEGnet in F1 score and robustness to federation and partial participation, while using fewer parameters per communication round.

Complex Interpolation of Matrices with an application to Multi-Manifold Learning
Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation
SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions
AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models

Source: arXiv cs.LG | 2026-04-27

Related