# MSGM: A Multi-Scale Spatiotemporal Graph Mamba for EEG Emotion Recognition

arXiv: https://arxiv.org/abs/2507.15914 · HTML: https://mlsanity.com/paper/2507.15914/

## Key facts

- Cited by 4 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 15 of its 60 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Physiological signal modeling](https://mlsanity.com/ssm/physiological-signal-modeling/)

## Builds on (most cited first, 15 of 15)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting](https://mlsanity.com/paper/2402.05956/) (2024)
- [EEG-Based Emotion Recognition Using Regularized Graph Neural Networks](https://mlsanity.com/paper/1907.07835/) (2019)
- [TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognition](https://mlsanity.com/paper/2104.02935/) (2021)
- [LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interface](https://mlsanity.com/paper/2105.02786/) (2021)
- [EmT: A Novel Transformer for Generalized Cross-subject EEG Emotion Recognition](https://mlsanity.com/paper/2406.18345/) (2024)
- [PGCN: Pyramidal Graph Convolutional Network for EEG Emotion Recognition](https://mlsanity.com/paper/2302.02520/) (2023)
- [MASA-TCN: Multi-anchor Space-aware Temporal Convolutional Neural Networks for Continuous and Discrete EEG Emotion Recognition](https://mlsanity.com/paper/2308.16207/) (2023)
- [A Two-Stage Efficient 3-D CNN Framework for EEG Based Emotion Recognition](https://mlsanity.com/paper/2208.00883/) (2022)
- [A Comprehensive Survey on EEG-Based Emotion Recognition: A Graph-Based Perspective](https://mlsanity.com/paper/2408.06027/) (2024)
- [Multi-Source EEG Emotion Recognition via Dynamic Contrastive Domain Adaptation](https://mlsanity.com/paper/2408.10235/) (2024)
- [Multi-periodicity dependency Transformer based on spectrum offset for radio frequency fingerprint identification](https://mlsanity.com/paper/2408.07592/) (2024)

## Built on by (most cited first, 4 of 4)

- [MemMamba: Rethinking Memory Patterns in State Space Model](https://mlsanity.com/paper/2510.03279/) (2025)
- [A Multi-Scale Temporal Framework with Dynamic Fusion for EEG-Based Emotion Recognition](https://mlsanity.com/paper/2608.09088/) (2026)
- [NAKUL-Med: Spectral-Graph State Space Models with Dynamics Kernels for Medical Signals](https://mlsanity.com/paper/2605.00871/) (2026)
- [Graph Learning for Cross-Subject, Cross-Population EEG Emotion Decoding and Model-Derived Spatial-Spectral Neural Signatures](https://mlsanity.com/paper/2609.22103/) (2026)

## Abstract (arXiv)

EEG-based emotion recognition struggles with capturing multi-scale spatiotemporal dynamics and ensuring computational efficiency for real-time applications. Existing methods often oversimplify temporal granularity and spatial hierarchies, limiting accuracy. To overcome these challenges, we propose the Multi-Scale Spatiotemporal Graph Mamba (MSGM), a novel framework integrating multi-window temporal segmentation, bimodal spatial graph modeling, and efficient fusion via the Mamba architecture. By segmenting EEG signals across diverse temporal scales and constructing global-local graphs with neuroanatomical priors, MSGM effectively captures fine-grained emotional fluctuations and hierarchical brain connectivity. A multi-depth Graph Convolutional Network (GCN) and token embedding fusion module, paired with Mamba's state-space modeling, enable dynamic spatiotemporal interaction at linear complexity. Notably, with just one MSST-Mamba layer, MSGM surpasses leading methods in the field on the SEED, THU-EP, and FACED datasets, outperforming baselines in subject-independent emotion classification while achieving robust accuracy and millisecond-level inference on the NVIDIA Jetson Xavier NX.