mlsanityData to 7 Oct 2026

DynDepNet: Learning Time-Varying Dependency Structures from fMRI Data via Dynamic Graph Structure Learning

arXiv 2209.13513 ↗First posted 27 Sep 2022cs.LG stat.AP stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have demonstrated success in learning representations of brain graphs derived from functional magnetic resonance imaging (fMRI) data. However, existing GNN methods assume brain graphs are static over time and the graph adjacency matrix is known prior to model training. These assumptions contradict evidence that brain graphs are time-varying with a connectivity structure that depends on the choice of functional connectivity measure. Incorrectly representing fMRI data with noisy brain graphs can adversely affect GNN performance. To address this, we propose DynDepNet, a novel method for learning the optimal time-varying dependency structure of fMRI data induced by downstream prediction tasks. Experiments on real-world fMRI datasets, for the task of sex classification, demonstrate that DynDepNet achieves state-of-the-art results, outperforming the best baseline in terms of accuracy by approximately 8 and 6 percentage points, respectively. Furthermore, analysis of the learned dynamic graphs reveals prediction-related brain regions consistent with existing neuroscience literature.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 31 of its 82 references that are in the map. First posted on arXiv 27 Sep 2022.

Builds on

31 of 82 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2017Graph Attention Networkscited by 8,854
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2017Inductive Representation Learning on Large Graphscited by 6,284
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  11. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  12. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
19 more
  1. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  2. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  3. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  4. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  5. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
  6. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
  7. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 86
  8. 2022BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networkscited by 73
  9. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 70
  10. 2022FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generationcited by 66
  11. 2019Graph-Revised Convolutional Networkcited by 58
  12. 2020Spatio-Temporal Graph Convolution for Resting-State fMRI Analysiscited by 57
  13. 2020Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysiscited by 41
  14. 2019Graph Neural Network for Interpreting Task-fMRI Biomarkerscited by 40
  15. 2017An optimal transportation approach for assessing almost stochastic ordercited by 33
  16. 2016Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based examplecited by 31
  17. 2022deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networkscited by 28
  18. 2018Why Comparing Single Performance Scores Does Not Allow to Draw Conclusions About Machine Learning Approachescited by 15
  19. 2021A deep learning model for data-driven discovery of functional connectivitycited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 2; 2026: 1.

4 papers.

  1. 2023Large-scale Graph Representation Learning of Dynamic Brain Connectome with Transformerscited by 1
  2. 2026When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Seriescited by 1
  3. 2025A Brain-to-Population Graph Learning Framework for Diagnosing Brain Disorderscited by 0
  4. 2025A Dual-Attention Graph Network for fMRI Data Classificationcited by 0