# Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders

arXiv: https://arxiv.org/abs/1812.06857 · HTML: https://mlsanity.com/paper/1812.06857/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2018.

## Built on by (most cited first, 11 of 11)

- [EEG2Vec: Learning Affective EEG Representations via Variational Autoencoders](https://mlsanity.com/paper/2207.08002/) (2022)
- [Towards physiology-informed data augmentation for EEG-based BCIs](https://mlsanity.com/paper/2203.14392/) (2022)
- [LLMs Help Alleviate the Cross-Subject Variability in Brain Signal and Language Alignment](https://mlsanity.com/paper/2501.02621/) (2025)
- [AutoTransfer: Subject Transfer Learning with Censored Representations on Biosignals Data](https://mlsanity.com/paper/2112.09796/) (2021)
- [Review of Deep Representation Learning Techniques for Brain-Computer Interfaces and Recommendations](https://mlsanity.com/paper/2405.19345/) (2024)
- [On the use of generative deep neural networks to synthesize artificial multichannel EEG signals](https://mlsanity.com/paper/2102.08061/) (2021)
- [quEEGNet: Quantum AI for Biosignal Processing](https://mlsanity.com/paper/2210.00864/) (2022)
- [EEG-based Texture Roughness Classification in Active Tactile Exploration with Invariant Representation Learning Networks](https://mlsanity.com/paper/2102.08976/) (2021)
- [EEG-NeXt: A Modernized ConvNet for The Classification of Cognitive Activity from EEG](https://mlsanity.com/paper/2212.04951/) (2022)
- [Cross-Subject Deep Transfer Models for Evoked Potentials in Brain-Computer Interface](https://mlsanity.com/paper/2301.12322/) (2023)
- [Stabilizing Subject Transfer in EEG Classification with Divergence Estimation](https://mlsanity.com/paper/2310.08762/) (2023)

## Abstract (arXiv)

We introduce adversarial neural networks for representation learning as a novel approach to transfer learning in brain-computer interfaces (BCIs). The proposed approach aims to learn subject-invariant representations by simultaneously training a conditional variational autoencoder (cVAE) and an adversarial network. We use shallow convolutional architectures to realize the cVAE, and the learned encoder is transferred to extract subject-invariant features from unseen BCI users' data for decoding. We demonstrate a proof-of-concept of our approach based on analyses of electroencephalographic (EEG) data recorded during a motor imagery BCI experiment.