# Riemannian Geometry-Preserving Variational Autoencoder for MI-BCI Data Augmentation

arXiv: https://arxiv.org/abs/2603.10563 · HTML: https://mlsanity.com/paper/2603.10563/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [The largest EEG-based BCI reproducibility study for open science: the MOABB benchmark](https://mlsanity.com/paper/2404.15319/) (2024)
- [Parallel Transport on the Cone Manifold of SPD Matrices for Domain Adaptation](https://mlsanity.com/paper/1807.10479/) (2018)
- [Data Augmentation with Variational Autoencoders and Manifold Sampling](https://mlsanity.com/paper/2103.13751/) (2021)
- [Learning Weighted Submanifolds with Variational Autoencoders and Riemannian Variational Autoencoders](https://mlsanity.com/paper/1911.08147/) (2019)

## Built on by (most cited first, 1 of 1)

- [Generative Augmentation for EEG Motor Imagery Classification: A Class-Conditional VAE with Cycle-Consistent Decoder Refinement](https://mlsanity.com/paper/2607.22733/) (2026)

## Abstract (arXiv)

This paper addresses the challenge of generating synthetic electroencephalogram (EEG) covariance matrices for motor imagery brain-computer interface (MI-BCI) applications. Objective: We aim to develop a generative model capable of producing high-fidelity synthetic covariance matrices while preserving their symmetric positive-definite nature. Approach: We propose a Riemannian geometry-preserving variational autoencoder (RGP-VAE) integrating geometric mappings with a composite loss function combining Riemannian distance, tangent space reconstruction accuracy and generative diversity. Results: The model generates valid, representative EEG covariance matrices, while learning a subject-invariant latent space. Synthetic data proves practically useful for MI-BCI, with its impact depending on the paired classifier. Contribution: This work introduces and validates the RGP-VAE as a geometry-preserving generative model for EEG covariance matrices, highlighting its potential for signal privacy, scalability and data augmentation.