# EEG2Vec: Learning Affective EEG Representations via Variational Autoencoders

arXiv: https://arxiv.org/abs/2207.08002 · HTML: https://mlsanity.com/paper/2207.08002/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 16 Jul 2022.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [EEG-Based Emotion Recognition Using Regularized Graph Neural Networks](https://mlsanity.com/paper/1907.07835/) (2019)
- [Improved Variational Autoencoders for Text Modeling using Dilated Convolutions](https://mlsanity.com/paper/1702.08139/) (2017)
- [EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals](https://mlsanity.com/paper/1806.01875/) (2018)
- [Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks](https://mlsanity.com/paper/1511.06448/) (2015)
- [Data Augmentation for Enhancing EEG-based Emotion Recognition with Deep Generative Models](https://mlsanity.com/paper/2006.05331/) (2020)
- [Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification](https://mlsanity.com/paper/1901.07429/) (2019)
- [Domain-Invariant Representation Learning from EEG with Private Encoders](https://mlsanity.com/paper/2201.11613/) (2022)
- [Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders](https://mlsanity.com/paper/1812.06857/) (2018)
- [Disentangled Adversarial Autoencoder for Subject-Invariant Physiological Feature Extraction](https://mlsanity.com/paper/2008.11426/) (2020)
- [Multi-Scale Neural network for EEG Representation Learning in BCI](https://mlsanity.com/paper/2003.02657/) (2020)
- [Adversarial Deep Learning in EEG Biometrics](https://mlsanity.com/paper/1903.11673/) (2019)
- [Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generation](https://mlsanity.com/paper/2104.08857/) (2021)
- [Universal Physiological Representation Learning with Soft-Disentangled Rateless Autoencoders](https://mlsanity.com/paper/2009.13453/) (2020)
- [Exploiting Multiple EEG Data Domains with Adversarial Learning](https://mlsanity.com/paper/2204.07777/) (2022)
- [Information Theoretic Feature Transformation Learning for Brain Interfaces](https://mlsanity.com/paper/1903.12235/) (2019)
- [Exploring Disentanglement with Multilingual and Monolingual VQ-VAE](https://mlsanity.com/paper/2105.01573/) (2021)
- [Multimodal Emotion Recognition Using Multimodal Deep Learning](https://mlsanity.com/paper/1602.08225/) (2016)
- [Hierarchical Graphical Models for Context-Aware Hybrid Brain-Machine Interfaces](https://mlsanity.com/paper/1809.05635/) (2018)
- [On the use of generative deep neural networks to synthesize artificial multichannel EEG signals](https://mlsanity.com/paper/2102.08061/) (2021)

## Built on by (most cited first, 15 of 15)

- [NeurIPT: Foundation Model for Neural Interfaces](https://mlsanity.com/paper/2510.16548/) (2025)
- [Deep Generative Models for Physiological Signals: A Systematic Literature Review](https://mlsanity.com/paper/2307.06162/) (2023)
- [ALFEE: Adaptive Large Foundation Model for EEG Representation](https://mlsanity.com/paper/2505.06291/) (2025)
- [vEEGNet: learning latent representations to reconstruct EEG raw data via variational autoencoders](https://mlsanity.com/paper/2312.09449/) (2023)
- [NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Training](https://mlsanity.com/paper/2509.26301/) (2025)
- [Variational Mixture of Graph Neural Experts for Alzheimer's Disease Recognition across Frequency Bands in EEG Brain Networks](https://mlsanity.com/paper/2510.11917/) (2025)
- [Variational Autoencoder Learns Better Feature Representations for EEG-based Obesity Classification](https://mlsanity.com/paper/2302.00789/) (2023)
- [Synthesizing Affective Neurophysiological Signals Using Generative Models: A Review Paper](https://mlsanity.com/paper/2306.03112/) (2023)
- [TS-MoCo: Time-Series Momentum Contrast for Self-Supervised Physiological Representation Learning](https://mlsanity.com/paper/2306.06522/) (2023)
- [Continuous Indeterminate Probability Neural Network](https://mlsanity.com/paper/2303.12964/) (2023)
- [hvEEGNet: exploiting hierarchical VAEs on EEG data for neuroscience applications](https://mlsanity.com/paper/2312.00799/) (2023)
- [ISAM-MTL: Cross-subject multi-task learning model with identifiable spikes and associative memory networks](https://mlsanity.com/paper/2501.18089/) (2025)
- [Synthetic Data Generation for Brain-Computer Interfaces: Overview, Benchmarking, and Future Directions](https://mlsanity.com/paper/2603.12296/) (2026)
- [Generative Augmentation for EEG Motor Imagery Classification: A Class-Conditional VAE with Cycle-Consistent Decoder Refinement](https://mlsanity.com/paper/2607.22733/) (2026)
- [DenoFlow: Flow Matching for SSVEP Denoising under Real Physiological Artifacts](https://mlsanity.com/paper/2610.08817/) (2026)

## Abstract (arXiv)

There is a growing need for sparse representational formats of human affective states that can be utilized in scenarios with limited computational memory resources. We explore whether representing neural data, in response to emotional stimuli, in a latent vector space can serve to both predict emotional states as well as generate synthetic EEG data that are participant- and/or emotion-specific. We propose a conditional variational autoencoder based framework, EEG2Vec, to learn generative-discriminative representations from EEG data. Experimental results on affective EEG recording datasets demonstrate that our model is suitable for unsupervised EEG modeling, classification of three distinct emotion categories (positive, neutral, negative) based on the latent representation achieves a robust performance of 68.49%, and generated synthetic EEG sequences resemble real EEG data inputs to particularly reconstruct low-frequency signal components. Our work advances areas where affective EEG representations can be useful in e.g., generating artificial (labeled) training data or alleviating manual feature extraction, and provide efficiency for memory constrained edge computing applications.