mlsanityData to 7 Oct 2026

Machine Learning on Dynamic Functional Connectivity: Promise, Pitfalls, and Interpretations

arXiv 2409.11377 ↗First posted 17 Sep 2024cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

An unprecedented amount of existing functional Magnetic Resonance Imaging (fMRI) data provides a new opportunity to understand the relationship between functional fluctuation and human cognition/behavior using a data-driven approach. To that end, tremendous efforts have been made in machine learning to predict cognitive states from evolving volumetric images of blood-oxygen-level-dependent (BOLD) signals. Due to the complex nature of brain function, however, the evaluation on learning performance and discoveries are not often consistent across current state-of-the-arts (SOTA). By capitalizing on large-scale existing neuroimaging data (34,887 data samples from six public databases), we seek to establish a well-founded empirical guideline for designing deep models for functional neuroimages by linking the methodology underpinning with knowledge from the neuroscience domain. Specifically, we put the spotlight on (1) What is the current SOTA performance in cognitive task recognition and disease diagnosis using fMRI? (2) What are the limitations of current deep models? and (3) What is the general guideline for selecting the suitable machine learning backbone for new neuroimaging applications? We have conducted a comprehensive evaluation and statistical analysis, in various settings, to answer the above outstanding questions.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 18 of its 80 references that are in the map. First posted on arXiv 17 Sep 2024.

Builds on

18 of 80 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  6. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  7. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 154
  8. 2022Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Datacited by 39
  9. 2023NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomicscited by 33
  10. 2020AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecastingcited by 26
  11. 2022BolT: Fused Window Transformers for fMRI Time Series Analysiscited by 23
  12. 2022Data-Driven Network Neuroscience: On Data Collection and Benchmarkcited by 12
6 more
  1. 2019Simple 1-D Convolutional Networks for Resting-State fMRI Based Classification in Autismcited by 11
  2. 2023Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionalscited by 7
  3. 2024Learning to Approximate Adaptive Kernel Convolution on Graphscited by 6
  4. 2022Benchmarking Graph Neural Networks for FMRI analysiscited by 4
  5. 2023DeepGraphDMD: Interpretable Spatio-Temporal Decomposition of Non-linear Functional Brain Network Dynamicscited by 2
  6. 2019Learning Multi-resolution Graph Edge Embedding for Discovering Brain Network Dysfunction in Neurological Disorderscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Large Connectome Model: An fMRI Foundation Model of Brain Connectomes Empowered by Brain-Environment Interaction in Multitask Learning Landscapecited by 4
  2. 2026GeoDynamics: A Geometric State-Space Neural Network for Understanding Brain Dynamics on Riemannian Manifoldscited by 1