Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling

• URL: http://arxiv.org/abs/2510.03027v2
• Date: Thu, 16 Oct 2025 04:34:31 GMT
• Title: Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling
• Abstract summary: EEG signals have inherent anti-correlations that are well modeled by negative edges in a finite graph.<n>We build lightweight and interpretable transformer-like neural nets by unrolling a spectral denoising algorithm for signals on a balanced signed graph.<n>Experiments show that our method achieves classification performance comparable to representative deep learning schemes.
• Score: 22.934749236365178
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Generative Diffusion Models of Stochastic Graph Signals [74.4097723209053]
  This paper tackles problems of conditional graph signal generative modeling and tackles them with a single denoising diffusion framework.<n>We learn a reverse diffusion process, parametrized by graph neural networks (GNNs), that draws graph signals conditioned directly on the graph topology and on node-feature side information.<n>We demonstrate our method on two generative tasks: stock price forecasting and optimal wireless resource allocation, with extensive numerical results in both domains.
  arXiv  Detail & Related papers  (2026-07-07T22:02:13Z)
• Directed Graph Topology Inference via Graph Filter Identification [54.541275287889164]
  We address the problem of inferring a directed network from nodal measurements generated by a graph convolutional filter.<n>A joint graph filter and topology identification algorithm is also proposed, which alternates between the aforementioned steps to offer improved sample complexity.
  arXiv  Detail & Related papers  (2026-06-25T18:25:57Z)
• Signed Graph Learning: Algorithms and Theory [17.374356596021936]
  Real-world data is often represented through the relationships between data samples, forming a graph structure.<n>Current graph learning research has primarily focused on unsigned graphs.<n>We develop a method for capturing a set of smooth signed graph signals.
  arXiv  Detail & Related papers  (2025-07-13T17:33:26Z)
• Efficient Learning of Balanced Signed Graphs via Sparse Linear Programming [26.334739062500674]
  A balanced signed graph has eigenvectors that map via a simple linear transform to ones in a corresponding positive graph.<n>We propose an efficient method to learn a balanced signed graph Laplacian directly from data.
  arXiv  Detail & Related papers  (2025-06-02T16:09:51Z)
• DFGNN: Dual-frequency Graph Neural Network for Sign-aware Feedback [51.72177873832969]
  We propose a novel model that models positive and negative feedback from a frequency filter perspective. We conduct extensive experiments on real-world datasets and demonstrate the effectiveness of the proposed model.
  arXiv  Detail & Related papers  (2024-05-24T07:07:41Z)
• Smoothed Graph Contrastive Learning via Seamless Proximity Integration [30.247207861739245]
  Graph contrastive learning (GCL) aligns node representations by classifying node pairs into positives and negatives. We present a Smoothed Graph Contrastive Learning model (SGCL) that injects proximity information associated with positive/negative pairs in the contrastive loss. The proposed SGCL adjusts the penalties associated with node pairs in contrastive loss by incorporating three distinct smoothing techniques.
  arXiv  Detail & Related papers  (2024-02-23T11:32:46Z)
• Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution [112.3443939502313]
  We propose a unified graph signal sampling framework which enjoys the benefits of graph signal analysis and processing. The key idea is to transform each user's ratings on the items to a function (signal) on the vertices of an item-item graph. For the online setting, we develop a Bayesian extension, i.e., BGS-IMC which considers continuous random Gaussian noise in the graph Fourier domain.
  arXiv  Detail & Related papers  (2023-02-08T08:17:43Z)
• Signed Graph Neural Networks: A Frequency Perspective [14.386571627652975]
  Graph convolutional networks (GCNs) are designed for unsigned graphs containing only positive links. We propose two different signed graph neural networks, one keeps only low-frequency information and one also retains high-frequency information.
  arXiv  Detail & Related papers  (2022-08-15T16:42:18Z)
• Embedding Signals on Knowledge Graphs with Unbalanced Diffusion Earth Mover's Distance [63.203951161394265]
  In modern machine learning it is common to encounter large graphs that arise via interactions or similarities between observations in many domains. We propose to compare and organize such datasets of graph signals by using an earth mover's distance (EMD) with a geodesic cost over the underlying graph. In each case, we show that UDEMD-based embeddings find accurate distances that are highly efficient compared to other methods.
  arXiv  Detail & Related papers  (2021-07-26T17:19:02Z)
• Learning Frequency Domain Approximation for Binary Neural Networks [68.79904499480025]
  We propose to estimate the gradient of sign function in the Fourier frequency domain using the combination of sine functions for training BNNs. The experiments on several benchmark datasets and neural architectures illustrate that the binary network learned using our method achieves the state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2021-03-01T08:25:26Z)
• A Hierarchical Graph Signal Processing Approach to Inference from Spatiotemporal Signals [14.416786768268233]
  Motivated by the emerging area of graph signal processing (GSP), we introduce a novel method to draw inference from signals. In this paper we leverage techniques to develop a hierarchical feature extraction approach. We test our approach on the intracranial EEG (iEEG) data set of the K aggle seizure detection contest.
  arXiv  Detail & Related papers  (2020-10-25T17:08:13Z)
• Unrolling of Deep Graph Total Variation for Image Denoising [106.93258903150702]
  In this paper, we combine classical graph signal filtering with deep feature learning into a competitive hybrid design. We employ interpretable analytical low-pass graph filters and employ 80% fewer network parameters than state-of-the-art DL denoising scheme DnCNN.
  arXiv  Detail & Related papers  (2020-10-21T20:04:22Z)
• Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection [54.98042023365694]
  We propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples. The proposed model consists of two sub-models parameterized by neural networks.
  arXiv  Detail & Related papers  (2020-07-23T18:47:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.