mlsanityData to 7 Oct 2026

EEG2Vec: Learning Affective EEG Representations via Variational Autoencoders

arXiv 2207.08002 ↗First posted 16 Jul 2022cs.LG cs.AI eess.SPcited by 14

Not on the map. Why?

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.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 25 of its 59 references that are in the map. First posted on arXiv 16 Jul 2022.

Builds on

25 of 59 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  6. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 616
  7. 2019EEG-Based Emotion Recognition Using Regularized Graph Neural Networkscited by 97
  8. 2017Improved Variational Autoencoders for Text Modeling using Dilated Convolutionscited by 81
  9. 2018EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signalscited by 46
  10. 2015Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networkscited by 45
  11. 2020Data Augmentation for Enhancing EEG-based Emotion Recognition with Deep Generative Modelscited by 21
  12. 2019Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classificationcited by 12
13 more
  1. 2022Domain-Invariant Representation Learning from EEG with Private Encoderscited by 12
  2. 2018Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoderscited by 11
  3. 2020Disentangled Adversarial Autoencoder for Subject-Invariant Physiological Feature Extractioncited by 11
  4. 2020Multi-Scale Neural network for EEG Representation Learning in BCIcited by 10
  5. 2019Adversarial Deep Learning in EEG Biometricscited by 9
  6. 2021Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generationcited by 9
  7. 2020Universal Physiological Representation Learning with Soft-Disentangled Rateless Autoencoderscited by 7
  8. 2022Exploiting Multiple EEG Data Domains with Adversarial Learningcited by 5
  9. 2019Information Theoretic Feature Transformation Learning for Brain Interfacescited by 4
  10. 2021Exploring Disentanglement with Multilingual and Monolingual VQ-VAEcited by 4
  11. 2016Multimodal Emotion Recognition Using Multimodal Deep Learningcited by 3
  12. 2018Hierarchical Graphical Models for Context-Aware Hybrid Brain-Machine Interfacescited by 3
  13. 2021On the use of generative deep neural networks to synthesize artificial multichannel EEG signalscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 0; 2025: 5; 2026: 2.

14 papers.

Sort:

  1. 2025NeurIPT: Foundation Model for Neural Interfacescited by 9
  2. 2023Deep Generative Models for Physiological Signals: A Systematic Literature Reviewcited by 7
  3. 2023vEEGNet: learning latent representations to reconstruct EEG raw data via variational autoencoderscited by 2
  4. 2025ALFEE: Adaptive Large Foundation Model for EEG Representationcited by 2
  5. 2025Variational Mixture of Graph Neural Experts for Alzheimer's Disease Recognition across Frequency Bands in EEG Brain Networkscited by 2
  6. 2023Variational Autoencoder Learns Better Feature Representations for EEG-based Obesity Classificationcited by 1
  7. 2023Synthesizing Affective Neurophysiological Signals Using Generative Models: A Review Papercited by 1
  8. 2023TS-MoCo: Time-Series Momentum Contrast for Self-Supervised Physiological Representation Learningcited by 1
  9. 2025NeuroTTT: Bridging Pretraining-Downstream Task Misalignment in EEG Foundation Models via Test-Time Trainingcited by 1
  10. 2023Continuous Indeterminate Probability Neural Networkcited by 0
  11. 2023hvEEGNet: exploiting hierarchical VAEs on EEG data for neuroscience applicationscited by 0
  12. 2025ISAM-MTL: Cross-subject multi-task learning model with identifiable spikes and associative memory networkscited by 0
2 more
  1. 2026Synthetic Data Generation for Brain-Computer Interfaces: Overview, Benchmarking, and Future Directionscited by 0
  2. 2026Generative Augmentation for EEG Motor Imagery Classification: A Class-Conditional VAE with Cycle-Consistent Decoder Refinementcited by 0