T-SNN: Temporal Simplicial Neural Network for EEG Decoding

Abstract

Decoding brain states requires models that capture both the evolution of neural activity and interactions among groups of brain regions. Existing EEG methods often treat recordings as multivariate time series or represent functional connectivity with pairwise graphs, leaving dynamic higher-order interactions largely unmodeled. We introduce the Temporal Simplicial Neural Network (T-SNN), which represents EEG recordings as sequences of evolving simplicial complexes. By combining simplicial convolutions with recurrent updates, T-SNN jointly learns higher-order interactions and their temporal evolution. On the seven-class SEED-VII emotion recognition task, T-SNN outperforms convolutional, recurrent, graph-based, and Transformer methods in both trial-wise and cross-subject evaluations. Incorporating eye-movement features further improves performance, demonstrating the framework's potential for multimodal brain-state decoding.

Decoding motor imagery EEG signals by a deep learning network integrating multiscale filtering and temporal-channel attention mechanisms
Yong Zhu, Yongge Shi, Jianhua Wu +1
PLOS One23 Oct 2026Peer-reviewedCC BYFull textNeurosciencePLOSEurope PMC
Brain Decoding from a Deep Neural Network of Visual Memory Reveals the Maturation Trajectory of Memory Systems across Ages 3-7
X. GUO, Y. C. Leong, W. A. Bainbridge
bioRxiv3 Nov 2026PreprintCC BY-NC-NDFull textNeurosciencebioRxiv
Anterior part of fronto-temporal language network as the neural basis of morphologically structured word form processing: evidence from Korean morphologically complex word.
Jeahong Kim, Kichun Nam
BMC neuroscience1 Jul 2026Peer-reviewedCC BY-NC-NDFull textNeuroscience General medicineEurope PMCDOAJ
Graph attention spatio-temporal graph neural network based human–light interaction modeling for indoor lighting environments
Ting Gao, Lingling Sun
PLOS One25 Sep 2026Peer-reviewedCC BY 4.0Full textNeurosciencePLOS
Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets
Jens Egholm Pedersen, Tony Lindeberg, Peter Gerstoft
arXiv2 Oct 2026PreprintCC BY 4.0Full textNeurosciencearXiv

Cite

BibTeX RIS

BibTeX

@misc{malik2026tsnn,
  title = {{T-SNN: Temporal Simplicial Neural Network for EEG Decoding}},
  author = {Nikita Malik and Shubhajit Roy and Mohit Kataria and Isuru Herath and Suraj Yadav and Inés García-Redondo and Dhananjay Bhaskar},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.34002},
  eprint = {2609.34002},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.34002},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - T-SNN: Temporal Simplicial Neural Network for EEG Decoding
AU  - Nikita Malik
AU  - Shubhajit Roy
AU  - Mohit Kataria
AU  - Isuru Herath
AU  - Suraj Yadav
AU  - Inés García-Redondo
AU  - Dhananjay Bhaskar
PY  - 2026
DA  - 2026/09/27
PB  - arXiv
DO  - 10.48550/arxiv.2609.34002
UR  - https://arxiv.org/abs/2609.34002
AB  - Decoding brain states requires models that capture both the evolution of neural activity and interactions among groups of brain regions. Existing EEG methods often treat recordings as multivariate time series or represent functional connectivity with pairwise graphs, leaving dynamic higher-order interactions largely unmodeled. We introduce the Temporal Simplicial Neural Network (T-SNN), which represents EEG recordings as sequences of evolving simplicial complexes. By combining simplicial convolutions with recurrent updates, T-SNN jointly learns higher-order interactions and their temporal evolution. On the seven-class SEED-VII emotion recognition task, T-SNN outperforms convolutional, recurrent, graph-based, and Transformer methods in both trial-wise and cross-subject evaluations. Incorporating eye-movement features further improves performance, demonstrating the framework's potential for multimodal brain-state decoding.
ER  -

Abstract

Related

Cite