Universal Physiological Representation Learning with Soft-Disentangled Rateless Autoencoders


Human computer interaction (HCI) involves a multidisciplinary fusion of technologies, through which the control of external devices could be achieved by monitoring physiological status of users. However, physiological biosignals often vary across users and recording sessions due to unstable physical/mental conditions and taskirrelevant activities. To deal with this challenge, we propose a method of adversarial feature encoding with the concept of a Rateless Autoencoder (RAE), in order to exploit disentangled, nuisance-robust, and universal representations. We achieve a good trade-off between user-specific and task-relevant features by making use of the stochastic disentanglement of the latent representations by adopting additional adversarial networks. The proposed model is applicable to a wider range of unknown users and tasks as well as different classifiers. Results on cross-subject transfer evaluations show the advantages of the proposed framework, with up to an 11.6% improvement in the average subject-transfer classification accuracy.


  • Related Publication

  •  Han, M., Ozdenizci, O., Koike-Akino, T., Wang, Y., Erdogmus, D., "Soft-Disentangled Adversarial Transfer Learning for Universal Physiological Feature Extraction", arXiv, September 2020.
    BibTeX arXiv
    • @article{Han2020sep2,
    • author = {Han, Mo and Ozdenizci, Ozan and Koike-Akino, Toshiaki and Wang, Ye and Erdogmus, Deniz},
    • title = {Soft-Disentangled Adversarial Transfer Learning for Universal Physiological Feature Extraction},
    • journal = {arXiv},
    • year = 2020,
    • month = sep,
    • url = {}
    • }