mlsanityData to 14 Oct 2026

BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck

arXiv 2205.03612 ↗First posted 7 May 2022eess.SP cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Developing a new diagnostic models based on the underlying biological mechanisms rather than subjective symptoms for psychiatric disorders is an emerging consensus. Recently, machine learning-based classifiers using functional connectivity (FC) for psychiatric disorders and healthy controls are developed to identify brain markers. However, existing machine learning-based diagnostic models are prone to over-fitting (due to insufficient training samples) and perform poorly in new test environment. Furthermore, it is difficult to obtain explainable and reliable brain biomarkers elucidating the underlying diagnostic decisions. These issues hinder their possible clinical applications. In this work, we propose BrainIB, a new graph neural network (GNN) framework to analyze functional magnetic resonance images (fMRI), by leveraging the famed Information Bottleneck (IB) principle. BrainIB is able to identify the most informative edges in the brain (i.e., subgraph) and generalizes well to unseen data. We evaluate the performance of BrainIB against 3 baselines and 7 state-of-the-art brain network classification methods on three psychiatric datasets and observe that our BrainIB always achieves the highest diagnosis accuracy. It also discovers the subgraph biomarkers which are consistent to clinical and neuroimaging findings. The source code and implementation details of BrainIB are freely available at GitHub repository (https://github.com/SJYuCNEL/brain-and-Information-Bottleneck/).

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 24 of its 90 references that are in the map. First posted on arXiv 7 May 2022.

Builds on

24 of 90 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  7. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  8. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  9. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  11. 2018MINE: Mutual Information Neural Estimationcited by 683
  12. 2020Parameterized Explainer for Graph Neural Networkcited by 426
12 more
  1. 2019Self-Attention Graph Poolingcited by 421
  2. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  3. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  4. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  5. 2020Graph Information Bottleneckcited by 168
  6. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  7. 2018Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Diseasecited by 99
  8. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  9. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  10. 2020Second-Order Pooling for Graph Neural Networkscited by 33
  11. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  12. 2021BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysiscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 9; 2026: 6.

17 papers.

Sort:

  1. 2023CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosiscited by 16
  2. 2025MvHo-IB: Multi-View Higher-Order Information Bottleneck for Brain Disorder Diagnosiscited by 8
  3. 2026Modeling Higher-Order Brain Interactions via a Multi-View Information Bottleneck Framework for fMRI-based Psychiatric Diagnosiscited by 3
  4. 2025Information Bottleneck-Guided Heterogeneous Graph Learning for Interpretable Neurodevelopmental Disorder Diagnosiscited by 2
  5. 2025BrainIB++: Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophreniacited by 2
  6. 2026PIME: Prototype-based Interpretable MCTS-Enhanced Brain Network Analysis for Disorder Diagnosiscited by 2
  7. 2024Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic reviewcited by 1
  8. 2025Spatio-Temporal Graph Deep Learning with Stochastic Differential Equations for Uncovering Alzheimer's Disease Progressioncited by 1
  9. 2025VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRIcited by 1
  10. 2025Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraintscited by 1
  11. 2025BrainHGT: A Hierarchical Graph Transformer for Interpretable Brain Network Analysiscited by 1
  12. 2025AI Models for Depressive Disorder Detection and Diagnosis: A Reviewcited by 0
5 more
  1. 2025Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identificationcited by 0
  2. 2026Continual Learning for fMRI-Based Brain Disorder Diagnosis via Functional Connectivity Matrices Generative Replaycited by 0
  3. 2026Distance-Aware Joint Spatio-Temporal Graph Contrastive Learning for Major Depressive Disorder Diagnosiscited by 0
  4. 2026SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosiscited by 0
  5. 2026Information Bottleneck-Guided Adaptive Hypergraph Transformer for Brain Disease Diagnosiscited by 0