# Disentangled Adversarial Autoencoder for Subject-Invariant Physiological Feature Extraction

arXiv: https://arxiv.org/abs/2008.11426 · HTML: https://mlsanity.com/paper/2008.11426/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2020.

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

- [EEG2Vec: Learning Affective EEG Representations via Variational Autoencoders](https://mlsanity.com/paper/2207.08002/) (2022)
- [DAVA: Disentangling Adversarial Variational Autoencoder](https://mlsanity.com/paper/2303.01384/) (2023)
- [EEG Decoding for Datasets with Heterogenous Electrode Configurations using Transfer Learning Graph Neural Networks](https://mlsanity.com/paper/2306.13109/) (2023)
- [Exploiting Multiple EEG Data Domains with Adversarial Learning](https://mlsanity.com/paper/2204.07777/) (2022)
- [Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond](https://mlsanity.com/paper/2210.06295/) (2022)
- [AutoTransfer: Subject Transfer Learning with Censored Representations on Biosignals Data](https://mlsanity.com/paper/2112.09796/) (2021)
- [quEEGNet: Quantum AI for Biosignal Processing](https://mlsanity.com/paper/2210.00864/) (2022)
- [Deep clustering using adversarial net based clustering loss](https://mlsanity.com/paper/2412.08933/) (2024)
- [Towards Cross-Subject EMG Pattern Recognition via Dual-Branch Adversarial Feature Disentanglement](https://mlsanity.com/paper/2506.08555/) (2025)
- [Omni-modal decomposition autoencoders learn full-stack wearable disentangled representations](https://mlsanity.com/paper/2608.07385/) (2026)
- [From Stress to Affect: Multimodal Deep Learning for Physiological Emotion Recognition Across Wearable Sensor Modalities](https://mlsanity.com/paper/2609.20991/) (2026)

## Abstract (arXiv)

Recent developments in biosignal processing have enabled users to exploit their physiological status for manipulating devices in a reliable and safe manner. One major challenge of physiological sensing lies in the variability of biosignals across different users and tasks. To address this issue, we propose an adversarial feature extractor for transfer learning to exploit disentangled universal representations. We consider the trade-off between task-relevant features and user-discriminative information by introducing additional adversary and nuisance networks in order to manipulate the latent representations such that the learned feature extractor is applicable to unknown users and various tasks. Results on cross-subject transfer evaluations exhibit the benefits of the proposed framework, with up to 8.8% improvement in average accuracy of classification, and demonstrate adaptability to a broader range of subjects.