# Generative Augmentation for EEG Motor Imagery Classification: A Class-Conditional VAE with Cycle-Consistent Decoder Refinement

arXiv: https://arxiv.org/abs/2607.22733 · HTML: https://mlsanity.com/paper/2607.22733/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 15 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 6 of 6)

- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [RAVE: A variational autoencoder for fast and high-quality neural audio synthesis](https://mlsanity.com/paper/2111.05011/) (2021)
- [Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders](https://mlsanity.com/paper/1804.10469/) (2018)
- [EEG2Vec: Learning Affective EEG Representations via Variational Autoencoders](https://mlsanity.com/paper/2207.08002/) (2022)
- [vEEGNet: learning latent representations to reconstruct EEG raw data via variational autoencoders](https://mlsanity.com/paper/2312.09449/) (2023)
- [Riemannian Geometry-Preserving Variational Autoencoder for MI-BCI Data Augmentation](https://mlsanity.com/paper/2603.10563/) (2026)

## Abstract (arXiv)

We investigate whether a generative model can supply useful synthetic motor-imagery (MI) electroencephalography (EEG) trials that improve the accuracy of independent downstream classifiers. We train a class-conditional variational autoencoder (CVAE) with an integrated latent classifier on the Zhou motor-imagery dataset, using the learned per-class prior as a generator: sampling the prior for a given label and decoding it into a synthetic, label-consistent signal. A constraint on the covariance matrix of the generated data encourages preservation of covariance structure, and the model is trained with a schedule that alternates ordinary VAE training with a decoder-focused phase that sharpens the generative pathway used for augmentation. We measure the effect of adding synthetic trials to the training set under two evaluation protocols -- within-user (pooled 60/20/20 split across subjects) and cross-user (leave-one-subject-out, LOSO) -- across four representative EEG classification pipelines: Common Spatial Patterns with Linear Discriminant Analysis (CSP+LDA), tangent-space features with a Support Vector Machine (TGSP+SVM), Minimum Distance to Riemannian Mean (MDM), and a neural network based on EEGNetv4 (henceforth EEGNet). Results are aggregated across independent augmentation draws, random seeds (within-user), or leave-one-subject-out folds (cross-user), with uncertainty reported as 95% confidence intervals (Student's t-distribution) computed over per-seed/per-fold averages. We find that synthetic EEG from the CVAE is most credible as a source of class-structured, covariance-like data rather than as a substitute for real raw EEG: it can raise the point estimate for MDM, but the broader augmentation claim remains conservative -- observed gains are small and classifier-dependent.