mlsanityData to 7 Oct 2026

Graph Neural Network for Interpreting Task-fMRI Biomarkers

arXiv 1907.01661 ↗First posted 2 Jul 2019cs.LG cs.CV eess.IVcited by 40

Not on the map. Why?

Abstract (arXiv)

Finding the biomarkers associated with ASD is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. A promising approach to identify biomarkers is using Graph Neural Networks (GNNs), which can be used to analyze graph structured data, i.e. brain networks constructed by fMRI. One way to interpret important features is through looking at how the classification probability changes if the features are occluded or replaced. The major limitation of this approach is that replacing values may change the distribution of the data and lead to serious errors. Therefore, we develop a 2-stage pipeline to eliminate the need to replace features for reliable biomarker interpretation. Specifically, we propose an inductive GNN to embed the graphs containing different properties of task-fMRI for identifying ASD and then discover the brain regions/sub-graphs used as evidence for the GNN classifier. We first show GNN can achieve high accuracy in identifying ASD. Next, we calculate the feature importance scores using GNN and compare the interpretation ability with Random Forest. Finally, we run with different atlases and parameters, proving the robustness of the proposed method. The detected biomarkers reveal their association with social behaviors. We also show the potential of discovering new informative biomarkers. Our pipeline can be generalized to other graph feature importance interpretation problems.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 10; 2023: 7; 2024: 7; 2025: 4; 2026: 2.

40 papers.

Sort:

By area:

  1. 2022Brain Network Transformercited by 92
  2. 2021Graph Neural Networks in Network Neurosciencecited by 91
  3. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 86
  4. 2022BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networkscited by 73
  5. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  6. 2022FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generationcited by 66
  7. 2023NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomicscited by 33
  8. 2022Unlearning Graph Classifiers with Limited Data Resourcescited by 31
  9. 2022BolT: Fused Window Transformers for fMRI Time Series Analysiscited by 23
  10. 2021Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identificationcited by 15
  11. 2024Graph Neural Networks for Brain Graph Learning: A Surveycited by 13
  12. 2022Differentially Private Graph Classification with GNNscited by 12
28 more
  1. 2024Contrasformer: A Brain Network Contrastive Transformer for Neurodegenerative Condition Identificationcited by 12
  2. 2023Learning High-Order Relationships of Brain Regionscited by 10
  3. 2021Ensemble manifold based regularized multi-modal graph convolutional network for cognitive ability predictioncited by 9
  4. 2022SoK: Differential Privacy on Graph-Structured Datacited by 9
  5. 2023R-Mixup: Riemannian Mixup for Biological Networkscited by 8
  6. 2021Multiplex Graph Networks for Multimodal Brain Network Analysiscited by 7
  7. 2022Graph Convolutional Networks for Multi-modality Medical Imaging: Methods, Architectures, and Clinical Applicationscited by 7
  8. 2025BrainOOD: Out-of-distribution Generalizable Brain Network Analysiscited by 7
  9. 2024BrainMAE: A Region-aware Self-supervised Learning Framework for Brain Signalscited by 6
  10. 2021Heterogeneous Graph-Based Multimodal Brain Network Learningcited by 5
  11. 2023Contrastive Graph Pooling for Explainable Classification of Brain Networkscited by 5
  12. 2021Forecasting Brain Activity Based on Models of Spatio-Temporal Brain Dynamics: A Comparison of Graph Neural Network Architecturescited by 4
  13. 2022DynDepNet: Learning Time-Varying Dependency Structures from fMRI Data via Dynamic Graph Structure Learningcited by 4
  14. 2022Benchmarking Graph Neural Networks for FMRI analysiscited by 4
  15. 2021Identifying Autism Spectrum Disorder Based on Individual-Aware Down-Sampling and Multi-Modal Learningcited by 3
  16. 2024Applications of interpretable deep learning in neuroimaging: a comprehensive reviewcited by 3
  17. 2021Effective and Interpretable fMRI Analysis via Functional Brain Network Generationcited by 2
  18. 2023PAMI: partition input and aggregate outputs for model interpretationcited by 2
  19. 2026Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classificationcited by 2
  20. 2023Edge-aware Hard Clustering Graph Pooling for Brain Imagingcited by 1
  21. 2025BrainHGT: A Hierarchical Graph Transformer for Interpretable Brain Network Analysiscited by 1
  22. 2023DDeMON: Ontology-based function prediction by Deep Learning from Dynamic Multiplex Networkscited by 0
  23. 2024Deconvolving Complex Neuronal Networks into Interpretable Task-Specific Connectomescited by 0
  24. 2024SpaRG: Sparsely Reconstructed Graphs for Generalizable fMRI Analysiscited by 0
  25. 2024Network Representation Learning for Biophysical Neural Network Analysiscited by 0
  26. 2025Ensemble-based graph representation of fMRI data for cognitive brain state classificationcited by 0
  27. 2025Are Heterogeneous Graph Neural Networks Truly Effective for Node Classification? A Causal Perspectivecited by 0
  28. 2026Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysiscited by 0