Graph neural networks (GNN) are increasingly used to classify EEG for tasks such as emotion recognition, motor imagery and neurological diseases and disorders. A wide range of methods have been proposed to design GNN-based classifiers. Therefore, there is a need for a systematic review and categorisation of these approaches. We exhaustively search the published literature on this topic and derive several categories for comparison. These categories highlight the similarities and differences among the methods. The results suggest a prevalence of spectral graph convolutional layers over spatial. Additionally, we identify standard forms of node features, with the most popular being the raw EEG signal and differential entropy. Our results summarise the emerging trends in GNN-based approaches for EEG classification. Finally, we discuss several promising research directions, such as exploring the potential of transfer learning methods and appropriate modelling of cross-frequency interactions.
Graph Neural Networks in EEG-based Emotion Recognition: A Survey
Nanyang Technological University, Singapore(南洋理工大学);Xi’an Jiaotong University, Xi’an, China(西安交通大学);Imperial College London, London, UK(伦敦帝国理工学院);Amazon, Seattle, WA, USA(亚马逊);Carnegie Mellon University, Pittsburgh, PA, USA(卡内基梅隆大学);Uber Technologies, Inc., USA(Uber Technologies, Inc.);School of Computer Science, Central China Normal University, Wuhan, China(中央财经大学计算机学院);Institute of Automation, Chinese Academy of Sciences, Beijing, China(中国科学院自动化研究所)
Comparison of Attention-based Deep Learning Models for EEG Classification
University of Padova(帕多瓦大学);National, Inter-University Consortium for Telecommunications (CNIT)(全国大学校际电信联盟(CNIT));National Center of Neurology and Psychiatry(国立精神神经医疗研究中心);University of Milano-Bicocca(米兰比可卡大学);Wroclaw University of Science and Technology(弗罗茨瓦夫理工大学)
Motor imagery classification using EEG spectrograms
University of Engineering and Technology, Taxila(塔克西拉工程技术大学);Children’s National Hospital(国家儿童医院);Sheikh Zayed Institute for Pediatric Surgical Innovation(谢赫·扎耶德儿科外科创新研究所);George Washington University(乔治华盛顿大学)
PHINN-EEG: Topological Time-Series Analysis of Dream-State EEG -- Dynamic Betti Curves for Dream Content Classification and Topology-Conditioned Neural Signal Synthesis
Human brain state classification via permutation entropy of EEG phase dynamics across consciousness levels and inattentive-type ADHD
Asia Pacific Center for Theoretical Physics(亚太理论物理中心);Pohang University of Science and Technology(浦项科技大学);Center for Neuroscience Imaging Research, Institute for Basic Science(基础科学研究院神经科学成像研究中心);Sungkyunkwan University(成均馆大学);Center for Artificial Intelligence and Natural Sciences, Korea Institute for Advanced Study(韩国高等研究院人工智能与自然科学中心);Research Institute of Slowave Inc.(Slowave公司研究所);Department of Anesthesiology, University of Michigan Medical School(密歇根大学医学院麻醉学系)