GroupINN: Grouping-based Interpretable Neural Network for Classification of Limited, Noisy Brain Data

By Yujun Yan, Jiong Zhu, Marlena Duda, Eric Solarz, Chandra Sekhar Sripada, Danai Koutra. 2019

121 citations recorded by the source corpus.

Mapping the human brain, or understanding how certain brain regions relate to specific aspects of cognition, has been and remains an active area of neuroscience research. Functional magnetic resonance imaging (fMRI) data---in the form of images, time series or graphs---are central in this research, but pose many challenges in phenotype prediction tasks (e.g., noisy, small training samples). Standardly employed handcrafted models and newly proposed neural network methods pose limitations in the expressive power and interpretability, respectively, in this context. In this work focusing on fMRI-derived brain graphs, a modality that partially handles some challenges of fMRI data, we propose a grouping-based interpretable neural network model, GroupINN, that effectively classifies cognitive performance with 85% fewer model parameters than baseline deep models, while also identifying the most predictive brain subnetworks within several task-specific contexts. Our method incorporates the idea of node grouping into the design of the neural network. That way, unlike other methods that employ clustering as a preprocessing step to reorder nodes, GroupINN learns the node grouping and extracts graph features jointly. Experiments on task-based fMRI datasets show that our method is $2.6-69\times$ faster than other deep models, while achieving comparable or better accuracy and providing interpretability.

Subfields: Artificial Intelligence, Cognitive Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

Citations in the corpus

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “In the medical field (also see later section), we have [122], [123] (uses Laplacian Eigenmap for interpretability) [124] (introduces a low-rank representation method for Autistic Spectrum Diagnosis).”
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks (2021, methodology): “…GNN variants have been proposed for different applications such as: computer vision (Satorras & Estrach, 2018), social science (Li & Goldwasser, 2019), biology (Yan et al., 2019), algorithmic tasks (Veličković et al., 2020; Yan et al., 2020), and inductive classification Hamilton et al. (2017).”
Explainable Machine Learning for Scientific Insights and Discoveries (2019, methodology): “Reference [102], for example, introduces a grouping layer in a graph-based NN called GroupINN to identify subgroups of”
BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis (2020, methodology): “In addition, although recent studies have investigated group-level ( Li et al., 2018; Venkataraman et al., 2016; Salman et al., 2019; Yan et al., 2019 ) and individual-level ( Brennan et al., 2019; Mahowald and Fedorenko, 2016; Li et al., 2019 ) neurological biomarkers, few GNN studies have…”