# Domain-Invariant Representation Learning from EEG with Private Encoders

arXiv: https://arxiv.org/abs/2201.11613 · HTML: https://mlsanity.com/paper/2201.11613/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 27 Jan 2022.

## Builds on (most cited first, 9 of 9)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Federated Transfer Learning for EEG Signal Classification](https://mlsanity.com/paper/2004.12321/) (2020)
- [MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition](https://mlsanity.com/paper/2107.07740/) (2021)
- [Protecting Privacy of Users in Brain-Computer Interface Applications](https://mlsanity.com/paper/1907.01586/) (2019)
- [Personalized Brain-Computer Interface Models for Motor Rehabilitation](https://mlsanity.com/paper/1705.03259/) (2017)
- [Time-Series Prediction of Proximal Aggression Onset in Minimally-Verbal Youth with Autism Spectrum Disorder Using Physiological Biosignals](https://mlsanity.com/paper/1809.09948/) (2018)

## Built on by (most cited first, 12 of 12)

- [EEG2Vec: Learning Affective EEG Representations via Variational Autoencoders](https://mlsanity.com/paper/2207.08002/) (2022)
- [EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs](https://mlsanity.com/paper/2305.00664/) (2023)
- [Exploiting Multiple EEG Data Domains with Adversarial Learning](https://mlsanity.com/paper/2204.07777/) (2022)
- [Domain Adaptation and Generalization on Functional Medical Images: A Systematic Survey](https://mlsanity.com/paper/2212.03176/) (2022)
- [Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordings](https://mlsanity.com/paper/2608.22420/) (2026)
- [TS-MoCo: Time-Series Momentum Contrast for Self-Supervised Physiological Representation Learning](https://mlsanity.com/paper/2306.06522/) (2023)
- [Playing With Neuroscience: Past, Present and Future of Neuroimaging and Games](https://mlsanity.com/paper/2403.15413/) (2024)
- [Unsupervised Pairwise Learning Optimization Framework for Cross-Corpus EEG-Based Emotion Recognition Based on Prototype Representation](https://mlsanity.com/paper/2508.11663/) (2025)
- [Hashing Learning with Hyper-Class Representation](https://mlsanity.com/paper/2206.02334/) (2022)
- [Federated deep transfer learning for EEG decoding using multiple BCI tasks](https://mlsanity.com/paper/2211.10976/) (2022)
- [PiRL: Participant-Invariant Representation Learning for Healthcare](https://mlsanity.com/paper/2211.12422/) (2022)
- [Differentially Private EEG Feature Anonymization: A Privacy-Utility Case Study in Clinical Neurophysiology](https://mlsanity.com/paper/2609.11777/) (2026)

## Abstract (arXiv)

Deep learning based electroencephalography (EEG) signal processing methods are known to suffer from poor test-time generalization due to the changes in data distribution. This becomes a more challenging problem when privacy-preserving representation learning is of interest such as in clinical settings. To that end, we propose a multi-source learning architecture where we extract domain-invariant representations from dataset-specific private encoders. Our model utilizes a maximum-mean-discrepancy (MMD) based domain alignment approach to impose domain-invariance for encoded representations, which outperforms state-of-the-art approaches in EEG-based emotion classification. Furthermore, representations learned in our pipeline preserve domain privacy as dataset-specific private encoding alleviates the need for conventional, centralized EEG-based deep neural network training approaches with shared parameters.