# EEG-GNN: Graph Neural Networks for Classification of Electroencephalogram (EEG) Signals

arXiv: https://arxiv.org/abs/2106.09135 · HTML: https://mlsanity.com/paper/2106.09135/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 16 Jun 2021.

## Builds on (most cited first, 9 of 9)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [Self-Attention Graph Pooling](https://mlsanity.com/paper/1904.08082/) (2019)
- [Order Matters: Sequence to sequence for sets](https://mlsanity.com/paper/1511.06391/) (2015)
- [Edge Contraction Pooling for Graph Neural Networks](https://mlsanity.com/paper/1905.10990/) (2019)
- [Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis](https://mlsanity.com/paper/2001.03690/) (2020)

## Built on by (most cited first, 28 of 28)

- [CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding](https://mlsanity.com/paper/2506.23075/) (2025)
- [Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2204.07321/) (2022)
- [Graph Neural Network-based EEG Classification: A Survey](https://mlsanity.com/paper/2310.02152/) (2023)
- [CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention](https://mlsanity.com/paper/2501.10885/) (2025)
- [Adaptive Gated Graph Convolutional Network for Explainable Diagnosis of Alzheimer's Disease using EEG Data](https://mlsanity.com/paper/2304.05874/) (2023)
- [Multi-modal Cross-domain Self-supervised Pre-training for fMRI and EEG Fusion](https://mlsanity.com/paper/2409.19130/) (2024)
- [EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks](https://mlsanity.com/paper/2509.15857/) (2025)
- [GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hint](https://mlsanity.com/paper/2305.15622/) (2023)
- [EEG Decoding for Datasets with Heterogenous Electrode Configurations using Transfer Learning Graph Neural Networks](https://mlsanity.com/paper/2306.13109/) (2023)
- [Graph Adapter of EEG Foundation Models for Parameter Efficient Fine Tuning](https://mlsanity.com/paper/2411.16155/) (2024)
- [Graph Convolutional Network with Connectivity Uncertainty for EEG-based Emotion Recognition](https://mlsanity.com/paper/2310.14165/) (2023)
- [ALFEE: Adaptive Large Foundation Model for EEG Representation](https://mlsanity.com/paper/2505.06291/) (2025)
- [Spatial-Functional awareness Transformer-based graph archetype contrastive learning for Decoding Visual Neural Representations from EEG](https://mlsanity.com/paper/2509.24761/) (2025)
- [ODEBrain: Continuous-Time EEG Graph for Modeling Dynamic Brain Networks](https://mlsanity.com/paper/2602.23285/) (2026)
- [Neural Brain Fields: A NeRF-Inspired Approach for Generating Nonexistent EEG Electrodes](https://mlsanity.com/paper/2601.00012/) (2025)
- [quEEGNet: Quantum AI for Biosignal Processing](https://mlsanity.com/paper/2210.00864/) (2022)
- [Improving EEG-based Emotion Recognition by Fusing Time-frequency And Spatial Representations](https://mlsanity.com/paper/2303.11421/) (2023)
- [Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-smoothness in Deep GNNs](https://mlsanity.com/paper/2312.08221/) (2023)
- [How Much Data is Enough? Optimization of Data Collection for Artifact Detection in EEG Recordings](https://mlsanity.com/paper/2411.11886/) (2024)
- [Statistical Test for Saliency Maps of Graph Neural Networks via Selective Inference](https://mlsanity.com/paper/2505.16893/) (2025)
- [FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontroller](https://mlsanity.com/paper/2603.26716/) (2026)
- [CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models](https://mlsanity.com/paper/2605.28792/) (2026)
- [EEG-NeXt: A Modernized ConvNet for The Classification of Cognitive Activity from EEG](https://mlsanity.com/paper/2212.04951/) (2022)
- [Functional Graph Contrastive Learning of Hyperscanning EEG Reveals Emotional Contagion Evoked by Stereotype-Based Stressors](https://mlsanity.com/paper/2308.13546/) (2023)
- [How Homogenizing the Channel-wise Magnitude Can Enhance EEG Classification Model?](https://mlsanity.com/paper/2407.20247/) (2024)
- [EEG-GMACN: Interpretable EEG Graph Mutual Attention Convolutional Network](https://mlsanity.com/paper/2412.17834/) (2024)
- [RepSPD: Enhancing SPD Manifold Representation in EEGs via Dynamic Graphs](https://mlsanity.com/paper/2602.22981/) (2026)
- [MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding](https://mlsanity.com/paper/2605.24523/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNN) have been frequently used to extract subject-invariant features from electroencephalogram (EEG) for classification tasks. This approach holds the underlying assumption that electrodes are equidistant analogous to pixels of an image and hence fails to explore/exploit the complex functional neural connectivity between different electrode sites. We overcome this limitation by tailoring the concepts of convolution and pooling applied to 2D grid-like inputs for the functional network of electrode sites. Furthermore, we develop various graph neural network (GNN) models that project electrodes onto the nodes of a graph, where the node features are represented as EEG channel samples collected over a trial, and nodes can be connected by weighted/unweighted edges according to a flexible policy formulated by a neuroscientist. The empirical evaluations show that our proposed GNN-based framework outperforms standard CNN classifiers across ErrP, and RSVP datasets, as well as allowing neuroscientific interpretability and explainability to deep learning methods tailored to EEG related classification problems. Another practical advantage of our GNN-based framework is that it can be used in EEG channel selection, which is critical for reducing computational cost, and designing portable EEG headsets.