mlsanityData to 14 Oct 2026

FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet

arXiv 2604.22494 ↗First posted 24 Apr 2026stat.ML cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 24 Apr 2026.

Builds on

20 of 27 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 628
  5. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  6. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 278
  7. 2016A Riemannian Network for SPD Matrix Learningcited by 162
  8. 2019Riemannian batch normalization for SPD neural networkscited by 72
  9. 2022SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEGcited by 53
  10. 2017Is Second-order Information Helpful for Large-scale Visual Recognition?cited by 44
  11. 2022On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyondcited by 38
  12. 2024The largest EEG-based BCI reproducibility study for open science: the MOABB benchmarkcited by 29
8 more
  1. 2023Infeasible Deterministic, Stochastic, and Variance-Reduction Algorithms for Optimization under Orthogonality Constraintscited by 18
  2. 2022Federated Learning on Riemannian Manifoldscited by 13
  3. 2024Geometric Neural Network based on Phase Space for BCI-EEG decodingcited by 5
  4. 2024Federated Learning on Riemannian Manifolds with Differential Privacycited by 5
  5. 2024Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Datacited by 5
  6. 2024Riemannian Federated Learning via Averaging Gradient Streamscited by 4
  7. 2024Classification of Buried Objects from Ground Penetrating Radar Images by using Second Order Deep Learning Modelscited by 3
  8. 2025Beyond R-barycenters: an effective averaging method on Stiefel and Grassmann manifoldscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A Stable Aggregation Method for Quantum Federated Learningcited by 0
  2. 2026Personalised federated learning for Riemannian and Euclidean EEG decodingcited by 0