mlsanityData to 7 Oct 2026

Learning High-Order Relationships of Brain Regions

arXiv 2312.02203 ↗First posted 2 Dec 2023q-bio.NC cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Discovering reliable and informative relationships among brain regions from functional magnetic resonance imaging (fMRI) signals is essential in phenotypic predictions. Most of the current methods fail to accurately characterize those interactions because they only focus on pairwise connections and overlook the high-order relationships of brain regions. We propose that these high-order relationships should be maximally informative and minimally redundant (MIMR). However, identifying such high-order relationships is challenging and under-explored due to the exponential search space and the absence of a tractable objective. In response to this gap, we propose a novel method named HYBRID which aims to extract MIMR high-order relationships from fMRI data. HYBRID employs a CONSTRUCTOR to identify hyperedge structures, and a WEIGHTER to compute a weight for each hyperedge, which avoids searching in exponential space. HYBRID achieves the MIMR objective through an innovative information bottleneck framework named multi-head drop-bottleneck with theoretical guarantees. Our comprehensive experiments demonstrate the effectiveness of our model. Our model outperforms the state-of-the-art predictive model by an average of 11.2%, regarding the quality of hyperedges measured by CPM, a standard protocol for studying brain connections.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 39 of its 90 references that are in the map. First posted on arXiv 2 Dec 2023.

Builds on

39 of 90 references.

References · 39

  1. 2017Neural Discrete Representation Learningcited by 4,650
  2. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  3. 2016Deep Variational Information Bottleneckcited by 915
  4. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  5. 2019Hypergraph Convolution and Hypergraph Attentioncited by 226
  6. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  7. 2020Graph Information Bottleneckcited by 168
  8. 2020Networks beyond pairwise interactions: structure and dynamicscited by 127
  9. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  10. 2021InfoGCL: Information-Aware Graph Contrastive Learningcited by 105
  11. 2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flowcited by 103
  12. 2019Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneckcited by 101
27 more
  1. 2022Brain Network Transformercited by 92
  2. 2019InfoBot: Transfer and Exploration via the Information Bottleneckcited by 78
  3. 2019Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentationcited by 74
  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. 2021What are higher-order networks?cited by 66
  7. 2022FBNETGEN: Task-aware GNN-based fMRI Analysis via Functional Brain Network Generationcited by 66
  8. 2021The physics of higher-order interactions in complex systemscited by 63
  9. 2019Learning Efficient Multi-agent Communication: An Information Bottleneck Approachcited by 60
  10. 2022Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysiscited by 58
  11. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  12. 2019Graph Neural Network for Interpreting Task-fMRI Biomarkerscited by 40
  13. 2022Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Datacited by 39
  14. 2023NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomicscited by 33
  15. 2019Quantifying High-order Interdependencies via Multivariate Extensions of the Mutual Informationcited by 30
  16. 2020Structural Patterns and Generative Models of Real-world Hypergraphscited by 29
  17. 2022Interpretable Geometric Deep Learning via Learnable Randomness Injectioncited by 27
  18. 2023Community-Aware Transformer for Autism Prediction in fMRI Connectomecited by 27
  19. 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discoverycited by 27
  20. 2022Unveiling the higher-order organization of multivariate time seriescited by 17
  21. 2021Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Explorationcited by 15
  22. 2015Learning Hypergraph-regularized Attribute Predictorscited by 13
  23. 2016Elastic Net Hypergraph Learning for Image Clustering and Semi-supervised Classificationcited by 9
  24. 2021A deep learning model for data-driven discovery of functional connectivitycited by 8
  25. 2022Multivariate Information Theory Uncovers Synergistic Subsystems of the Human Cerebral Cortexcited by 8
  26. 2023Toward Auto-evaluation with Confidence-based Category Relation-aware Regressioncited by 4
  27. 2023Inference-based statistical network analysis uncovers star-like brain functional architectures for internalizing psychopathology in childrencited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 2.

10 papers.

  1. 2025MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decodingcited by 14
  2. 2025Rethinking Functional Brain Connectome Analysis: Do Graph Deep Learning Models Helpcited by 8
  3. 2025MvHo-IB: Multi-View Higher-Order Information Bottleneck for Brain Disorder Diagnosiscited by 8
  4. 2026Modeling Higher-Order Brain Interactions via a Multi-View Information Bottleneck Framework for fMRI-based Psychiatric Diagnosiscited by 3
  5. 2025NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorderscited by 1
  6. 2025Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraintscited by 1
  7. 2025On the Limits of Applying Graph Transformers for Brain Connectome Classificationcited by 0
  8. 2025Brain PathoGraph Learningcited by 0
  9. 2025Fundamental Limits of Crystalline Equivariant Graph Neural Networks: A Circuit Complexity Perspectivecited by 0
  10. 2026Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysiscited by 0