# Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling

arXiv: https://arxiv.org/abs/2510.03027 · HTML: https://mlsanity.com/paper/2510.03027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing](https://mlsanity.com/paper/1912.10557/) (2019)
- [Graph Signal Processing: Overview, Challenges and Applications](https://mlsanity.com/paper/1712.00468/) (2017)
- [How to learn a graph from smooth signals](https://mlsanity.com/paper/1601.02513/) (2016)
- [Text-to-Image Diffusion Models are Zero-Shot Classifiers](https://mlsanity.com/paper/2303.15233/) (2023)
- [Learning graphs from data: A signal representation perspective](https://mlsanity.com/paper/1806.00848/) (2018)
- [White-Box Transformers via Sparse Rate Reduction](https://mlsanity.com/paper/2306.01129/) (2023)
- [EEG2Rep: Enhancing Self-supervised EEG Representation Through Informative Masked Inputs](https://mlsanity.com/paper/2402.17772/) (2024)
- [3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model](https://mlsanity.com/paper/1803.07252/) (2018)
- [MAtt: A Manifold Attention Network for EEG Decoding](https://mlsanity.com/paper/2210.01986/) (2022)
- [Graph Spectral Image Processing](https://mlsanity.com/paper/1801.04749/) (2018)
- [Denoising Masked AutoEncoders Help Robust Classification](https://mlsanity.com/paper/2210.06983/) (2022)
- [Graph Laplacian Regularization for Image Denoising: Analysis in the Continuous Domain](https://mlsanity.com/paper/1604.07948/) (2016)
- [Signed Graph Metric Learning via Gershgorin Disc Perfect Alignment](https://mlsanity.com/paper/2006.08816/) (2020)
- [Deep learning with convolutional neural networks for decoding and visualization of EEG pathology](https://mlsanity.com/paper/1708.08012/) (2017)
- [Localized Spectral Graph Filter Frames: A Unifying Framework, Survey of Design Considerations, and Numerical Comparison (Extended Cut)](https://mlsanity.com/paper/2006.11220/) (2020)
- [Unrolling of Deep Graph Total Variation for Image Denoising](https://mlsanity.com/paper/2010.11290/) (2020)
- [Fast Graph Sampling Set Selection Using Gershgorin Disc Alignment](https://mlsanity.com/paper/1907.06179/) (2019)
- [Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors](https://mlsanity.com/paper/2406.04090/) (2024)
- [Efficient Signed Graph Sampling via Balancing & Gershgorin Disc Perfect Alignment](https://mlsanity.com/paper/2208.08726/) (2022)
- [Efficient Learning of Balanced Signed Graphs via Iterative Linear Programming](https://mlsanity.com/paper/2409.07794/) (2024)
- [Unrolling Plug-and-Play Gradient Graph Laplacian Regularizer for Image Restoration](https://mlsanity.com/paper/2407.01469/) (2024)

## Abstract (arXiv)

Samples of brain signals collected by EEG sensors have inherent anti-correlations that are well modeled by negative edges in a finite graph. To differentiate epilepsy patients from healthy subjects using collected EEG signals, we build lightweight and interpretable transformer-like neural nets by unrolling a spectral denoising algorithm for signals on a balanced signed graph -- graph with no cycles of odd number of negative edges. A balanced signed graph has well-defined frequencies that map to a corresponding positive graph via similarity transform of the graph Laplacian matrices. We implement an ideal low-pass filter efficiently on the mapped positive graph via Lanczos approximation, where the optimal cutoff frequency is learned from data. Given that two balanced signed graph denoisers learn posterior probabilities of two different signal classes during training, we evaluate their reconstruction errors for binary classification of EEG signals. Experiments show that our method achieves classification performance comparable to representative deep learning schemes, while employing dramatically fewer parameters.