# Interpretable Sparsification of Brain Graphs: Better Practices and Effective Designs for Graph Neural Networks

arXiv: https://arxiv.org/abs/2306.14375 · HTML: https://mlsanity.com/paper/2306.14375/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 77 references that are in the map.
- First posted on arXiv 26 Jun 2023.

## Builds on (most cited first, 29 of 29)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [On Explainability of Graph Neural Networks via Subgraph Explorations](https://mlsanity.com/paper/2102.05152/) (2021)
- [PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2010.05788/) (2020)
- [GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2001.06216/) (2020)
- [Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks](https://mlsanity.com/paper/2102.06462/) (2021)
- [Understanding Attention and Generalization in Graph Neural Networks](https://mlsanity.com/paper/1905.02850/) (2019)
- [Explainability Techniques for Graph Convolutional Networks](https://mlsanity.com/paper/1905.13686/) (2019)
- [Graph Condensation for Graph Neural Networks](https://mlsanity.com/paper/2110.07580/) (2021)
- [Learning to Drop: Robust Graph Neural Network via Topological Denoising](https://mlsanity.com/paper/2011.07057/) (2020)
- [Evaluating Saliency Map Explanations for Convolutional Neural Networks: A User Study](https://mlsanity.com/paper/2002.00772/) (2020)
- [DIG: A Turnkey Library for Diving into Graph Deep Learning Research](https://mlsanity.com/paper/2103.12608/) (2021)
- [RelEx: A Model-Agnostic Relational Model Explainer](https://mlsanity.com/paper/2006.00305/) (2020)
- [Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network](https://mlsanity.com/paper/1502.06796/) (2015)
- [Graph Saliency Maps through Spectral Convolutional Networks: Application to Sex Classification with Brain Connectivity](https://mlsanity.com/paper/1806.01764/) (2018)
- [BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis](https://mlsanity.com/paper/2107.05097/) (2021)
- [Provable and practical approximations for the degree distribution using sublinear graph samples](https://mlsanity.com/paper/1710.08607/) (2017)
- [Graph analysis and modularity of brain functional connectivity networks: searching for the optimal threshold](https://mlsanity.com/paper/1705.06481/) (2017)
- [Statistical Challenges of Big Brain Network Data](https://mlsanity.com/paper/1709.09645/) (2017)

## Built on by (most cited first, 11 of 11)

- [A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation](https://mlsanity.com/paper/2402.03358/) (2024)
- [Boosting Detection in Crowd Analysis via Underutilized Output Features](https://mlsanity.com/paper/2308.16187/) (2023)
- [Graph Neural Networks for Brain Graph Learning: A Survey](https://mlsanity.com/paper/2406.02594/) (2024)
- [VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data](https://mlsanity.com/paper/2311.00996/) (2023)
- [Sparse Covariance Neural Networks](https://mlsanity.com/paper/2410.01669/) (2024)
- [BrainMAP: Multimodal Graph Learning For Efficient Brain Disease Localization](https://mlsanity.com/paper/2506.11178/) (2025)
- [Exploring Consistency in Graph Representations:from Graph Kernels to Graph Neural Networks](https://mlsanity.com/paper/2410.23748/) (2024)
- [Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning](https://mlsanity.com/paper/2602.07256/) (2026)
- [Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networks](https://mlsanity.com/paper/2410.21618/) (2024)
- [Brain PathoGraph Learning](https://mlsanity.com/paper/2509.21742/) (2025)
- [ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining](https://mlsanity.com/paper/2511.22866/) (2025)

## Abstract (arXiv)

Brain graphs, which model the structural and functional relationships between brain regions, are crucial in neuroscientific and clinical applications involving graph classification. However, dense brain graphs pose computational challenges including high runtime and memory usage and limited interpretability. In this paper, we investigate effective designs in Graph Neural Networks (GNNs) to sparsify brain graphs by eliminating noisy edges. While prior works remove noisy edges based on explainability or task-irrelevant properties, their effectiveness in enhancing performance with sparsified graphs is not guaranteed. Moreover, existing approaches often overlook collective edge removal across multiple graphs. To address these issues, we introduce an iterative framework to analyze different sparsification models. Our findings are as follows: (i) methods prioritizing interpretability may not be suitable for graph sparsification as they can degrade GNNs' performance in graph classification tasks; (ii) simultaneously learning edge selection with GNN training is more beneficial than post-training; (iii) a shared edge selection across graphs outperforms separate selection for each graph; and (iv) task-relevant gradient information aids in edge selection. Based on these insights, we propose a new model, Interpretable Graph Sparsification (IGS), which enhances graph classification performance by up to 5.1% with 55.0% fewer edges. The retained edges identified by IGS provide neuroscientific interpretations and are supported by well-established literature.