Robust EEG Classification via Graph Neural Networks
Keywords: EEG Classification, Graph Neural Networks, Dynamic Time Warping
Abstract: Electroencephalogram (EEG) classification has gained prominence due to its applications in medical diagnostics and brain-computer interfaces. However, EEG data is known to have a low signal-to-noise ratio, resulting in high variance in predictions across similar instances. To overcome this issue, we introduce RoGra, a novel approach leveraging residual graph convolutional networks for robust EEG classification. Our model incorporates dynamic time warping (DTW) to align temporal information and capture meaningful neighborhood relationships, enhancing robustness against artifacts. Experiments on three well-established EEG datasets demonstrate that RoGra outperforms baseline methods by up to 25\%, marking the largest improvement in EEG classification accuracy since the introduction of the seminal EEGNet. Our code is publically available.
Supplementary Material: zip
Primary Area: learning on time series and dynamical systems
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 9776
Loading