mlsanityData to 14 Oct 2026

Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models

arXiv 2211.11176 ↗First posted 21 Nov 2022cs.LG cs.AI eess.SPcited by 29

On the map: State-space sequence models (S4, Mamba) → Physiological signal modeling

Abstract (arXiv)

Multivariate biosignals are prevalent in many medical domains, such as electroencephalography, polysomnography, and electrocardiography. Modeling spatiotemporal dependencies in multivariate biosignals is challenging due to (1) long-range temporal dependencies and (2) complex spatial correlations between the electrodes. To address these challenges, we propose representing multivariate biosignals as time-dependent graphs and introduce GraphS4mer, a general graph neural network (GNN) architecture that improves performance on biosignal classification tasks by modeling spatiotemporal dependencies in biosignals. Specifically, (1) we leverage the Structured State Space architecture, a state-of-the-art deep sequence model, to capture long-range temporal dependencies in biosignals and (2) we propose a graph structure learning layer in GraphS4mer to learn dynamically evolving graph structures in the data. We evaluate our proposed model on three distinct biosignal classification tasks and show that GraphS4mer consistently improves over existing models, including (1) seizure detection from electroencephalographic signals, outperforming a previous GNN with self-supervised pre-training by 3.1 points in AUROC; (2) sleep staging from polysomnographic signals, a 4.1 points improvement in macro-F1 score compared to existing sleep staging models; and (3) 12-lead electrocardiogram classification, outperforming previous state-of-the-art models by 2.7 points in macro-F1 score.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Placed in Physiological signal modeling, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 57 of its 93 references that are in the map. First posted on arXiv 21 Nov 2022.

Builds on

57 of 93 references.

References · 57

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  3. 2018How Powerful are Graph Neural Networks?cited by 4,393
  4. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  5. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  7. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  8. 2020Reformer: The Efficient Transformercited by 1,668
  9. 2020Rethinking Attention with Performerscited by 1,601
  10. 2019Generating Long Sequences with Sparse Transformerscited by 1,546
  11. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  12. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
38 more
  1. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  2. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  3. 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 700
  4. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  5. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
  6. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
  7. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  8. 2020Inductive Representation Learning on Temporal Graphscited by 462
  9. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
  10. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  11. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 431
  12. 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 413
  13. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 387
  14. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  15. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 360
  16. 2015Unitary Evolution Recurrent Neural Networkscited by 294
  17. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 275
  18. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
  19. 2020A Note on Over-Smoothing for Graph Neural Networkscited by 249
  20. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
  21. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  22. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
  23. 2022It's Raw! Audio Generation with State-Space Modelscited by 171
  24. 2020Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XLcited by 158
  25. 2017DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEGcited by 157
  26. 2020Machine Learning on Graphs: A Model and Comprehensive Taxonomycited by 156
  27. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  28. 2016How to learn a graph from smooth signalscited by 146
  29. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  30. 2021Graph-Guided Network for Irregularly Sampled Multivariate Time Seriescited by 111
  31. 2020Lipschitz Recurrent Neural Networkscited by 89
  32. 2018The Temple University Hospital Seizure Detection Corpuscited by 83
  33. 2021Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysiscited by 76
  34. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 71
  35. 2020Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networkscited by 64
  36. 2019Predicting Path Failure In Time-Evolving Graphscited by 54
  37. 2021Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directionscited by 43
  38. 2019Dreem Open Datasets: Multi-Scored Sleep Datasets to compare Human and Automated sleep stagingcited by 33

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 6; 2025: 9; 2026: 10.

29 papers.

Sort:

By area:

  1. 2024Graph Mamba: Towards Learning on Graphs with State Space Modelscited by 86
  2. 2025EEG Foundation Models: A Critical Review of Current Progress and Future Directionscited by 32
  3. 2025LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysiscited by 26
  4. 2024Mamba-FETrack: Frame-Event Tracking via State Space Modelcited by 22
  5. 2023Learning Long Sequences in Spiking Neural Networkscited by 19
  6. 2023Graph Anomaly Detection in Time Series: A Surveycited by 18
  7. 2025CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attentioncited by 14
  8. 2025Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modelingcited by 10
  9. 2024SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learningcited by 9
  10. 2025EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networkscited by 8
  11. 2026LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosiscited by 7
  12. 2025BACE: Behavior-Adaptive Connectivity Estimation for Interpretable Graphs of Neural Dynamicscited by 6
17 more
  1. 2023Graph State-Space Models and Latent Relational Inferencecited by 4
  2. 2025Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Spacecited by 4
  3. 2025BioSerenity-E1: a self-supervised EEG model for medical applicationscited by 4
  4. 2023Contaminated Multivariate Time-Series Anomaly Detection with Spatio-Temporal Graph Conditional Diffusion Modelscited by 3
  5. 2026ODEBrain: Continuous-Time EEG Graph for Modeling Dynamic Brain Networkscited by 3
  6. 2026Optimizing EEG Graph Structure for Seizure Detection: An Information Bottleneck and Self-Supervised Learning Approachcited by 3
  7. 2024Parkinson's Disease Detection from Resting State EEG using Multi-Head Graph Structure Learning with Gradient Weighted Graph Attention Explanationscited by 2
  8. 2024Exploring Graph Mamba: A Comprehensive Survey on State-Space Models for Graph Learningcited by 2
  9. 2025Mentality: A Mamba-based Approach towards Foundation Models for EEGcited by 2
  10. 2024Recovering Time-Varying Networks From Single-Cell Datacited by 1
  11. 2026FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontrollercited by 1
  12. 2026CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Modelscited by 1
  13. 2026NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosiscited by 1
  14. 2026RepSPD: Enhancing SPD Manifold Representation in EEGs via Dynamic Graphscited by 0
  15. 2026DANCE: Detect and Classify Events in EEGcited by 0
  16. 2026F2STNet: Fair and Federated Spectral-Temporal Modeling for Graph Forecastingcited by 0
  17. 2026GRFBrain: Graph-Structured Rectified Flows for EEG Dynamic Modelingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025BioMamba: Leveraging Spectro-Temporal Embedding in Bidirectional Mamba for Enhanced Biosignal Classification
  2. 2024Deep Latent Variable Modeling of Physiological Signals
  3. 2026Spatiotemporal Hyperedges for EEG Seizure Detection and Prediction
  4. 2024EEG_RL-Net: Enhancing EEG MI Classification through Reinforcement Learning-Optimised Graph Neural Networks
  5. 2024Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG
  6. 2026PanLUNA: An Efficient and Robust Query-Unified Multimodal Model for Edge Biosignal Intelligence
  7. 2026GraM-Diff: A Unified Graph-Mamba Diffusion Framework for EEG-Based Alzheimer's Disease Data Generation and Diagnosis
  8. 2026CG-MambaNet: A spatiotemporal framework for cross-patient epileptic seizure prediction using CNN-GCN-Mamba-BiLSTM with event-level clinical evaluation