mlsanityData to 14 Oct 2026

Distributionally Robust Cross Subject EEG Decoding

arXiv 2308.11651 ↗First posted 19 Aug 2023eess.SP cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, deep learning has shown to be effective for Electroencephalography (EEG) decoding tasks. Yet, its performance can be negatively influenced by two key factors: 1) the high variance and different types of corruption that are inherent in the signal, 2) the EEG datasets are usually relatively small given the acquisition cost, annotation cost and amount of effort needed. Data augmentation approaches for alleviation of this problem have been empirically studied, with augmentation operations on spatial domain, time domain or frequency domain handcrafted based on expertise of domain knowledge. In this work, we propose a principled approach to perform dynamic evolution on the data for improvement of decoding robustness. The approach is based on distributionally robust optimization and achieves robustness by optimizing on a family of evolved data distributions instead of the single training data distribution. We derived a general data evolution framework based on Wasserstein gradient flow (WGF) and provides two different forms of evolution within the framework. Intuitively, the evolution process helps the EEG decoder to learn more robust and diverse features. It is worth mentioning that the proposed approach can be readily integrated with other data augmentation approaches for further improvements. We performed extensive experiments on the proposed approach and tested its performance on different types of corrupted EEG signals. The model significantly outperforms competitive baselines on challenging decoding scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 19 Aug 2023.

Builds on

21 of 37 references.

References · 21

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  4. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 628
  5. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 364
  6. 2019Deep learning-based electroencephalography analysis: a systematic reviewcited by 156
  7. 2015A Complete Recipe for Stochastic Gradient MCMCcited by 146
  8. 2020Robust Optimization for Fairness with Noisy Protected Groupscited by 78
  9. 2020Subject-Aware Contrastive Learning for Biosignalscited by 76
  10. 2020DADA: Differentiable Automatic Data Augmentationcited by 57
  11. 2018EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signalscited by 48
  12. 2022Data augmentation for learning predictive models on EEG: a systematic comparisoncited by 33
9 more
  1. 2022Improving Task-free Continual Learning by Distributionally Robust Memory Evolutioncited by 31
  2. 2020Class-Weighted Classification: Trade-offs and Robust Approachescited by 30
  3. 2021CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signalscited by 22
  4. 2020Learning from Heterogeneous EEG Signals with Differentiable Channel Reorderingcited by 16
  5. 2020Principled learning method for Wasserstein distributionally robust optimization with local perturbationscited by 14
  6. 2018Addressing Class Imbalance in Classification Problems of Noisy Signals by using Fourier Transform Surrogatescited by 10
  7. 2018Distributionally Robust Semi-Supervised Learning for People-Centric Sensingcited by 8
  8. 2021Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awarenesscited by 8
  9. 2018HAMLET: Interpretable Human And Machine co-LEarning Techniquecited by 4

Built on by

Not cited yet.