FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet

arXiv:2604.22494 · stat.ML, cs.LG · Submitted 2026-04-24 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-04-24

Updated: 2026-09-01

Terminology

• Federated Learning — 22× in this paper · explained in 15 episodes
• Stiefel manifold — 12× in this paper · explained in 2 episodes
• Aggregation — 10× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Data Heterogeneity — 2× in this paper · explained in 3 episodes
• F1 Score — 2× in this paper · explained in 3 episodes
• Riemannian optimization — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Differential Privacy — 1× in this paper · explained in 4 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Federated Learning (FL) — 1× in this paper · explained in 7 episodes
• Local Optimization — 1× in this paper · explained in 2 episodes

Sources

• Federated Learning on Riemannian Manifolds
• Federated Learning on Riemannian Manifolds with Differential Privacy
• Riemannian Federated Learning via Averaging Gradient Streams
• Adam: A Method for Stochastic Optimization
• The largest EEG-based BCI reproducibility study for open science: the MOABB benchmark
• FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey