# Structural Explanations for Graph Neural Networks using HSIC

arXiv: https://arxiv.org/abs/2302.02139 · HTML: https://mlsanity.com/paper/2302.02139/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 4 Feb 2023.

## Builds on (most cited first, 20 of 20)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction](https://mlsanity.com/paper/1811.05320/) (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)
- [XGNN: Towards Model-Level Explanations of Graph Neural Networks](https://mlsanity.com/paper/2006.02587/) (2020)
- [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)
- [A Rewriting System for Convex Optimization Problems](https://mlsanity.com/paper/1709.04494/) (2017)
- [PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models](https://mlsanity.com/paper/2104.07788/) (2021)
- [DIG: A Turnkey Library for Diving into Graph Deep Learning Research](https://mlsanity.com/paper/2103.12608/) (2021)
- [GraphSVX: Shapley Value Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.10482/) (2021)
- [Contrastive Graph Neural Network Explanation](https://mlsanity.com/paper/2010.13663/) (2020)
- [An Explainer for Temporal Graph Neural Networks](https://mlsanity.com/paper/2209.00807/) (2022)
- [Explaining Dynamic Graph Neural Networks via Relevance Back-propagation](https://mlsanity.com/paper/2207.11175/) (2022)

## Built on by (most cited first, 4 of 4)

- [No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets](https://mlsanity.com/paper/2502.02379/) (2025)
- [QGraphLIME - Explaining Quantum Graph Neural Networks](https://mlsanity.com/paper/2510.05683/) (2025)
- [QGShap: Quantum Acceleration for Faithful GNN Explanations](https://mlsanity.com/paper/2512.03099/) (2025)
- [Estimating Subgraph Importance with Structural Prior Domain Knowledge](https://mlsanity.com/paper/2605.12009/) (2026)

## Abstract (arXiv)

Graph neural networks (GNNs) are a type of neural model that tackle graphical tasks in an end-to-end manner. Recently, GNNs have been receiving increased attention in machine learning and data mining communities because of the higher performance they achieve in various tasks, including graph classification, link prediction, and recommendation. However, the complicated dynamics of GNNs make it difficult to understand which parts of the graph features contribute more strongly to the predictions. To handle the interpretability issues, recently, various GNN explanation methods have been proposed. In this study, a flexible model agnostic explanation method is proposed to detect significant structures in graphs using the Hilbert-Schmidt independence criterion (HSIC), which captures the nonlinear dependency between two variables through kernels. More specifically, we extend the GraphLIME method for node explanation with a group lasso and a fused lasso-based node explanation method. The group and fused regularization with GraphLIME enables the interpretation of GNNs in substructure units. Then, we show that the proposed approach can be used for the explanation of sequential graph classification tasks. Through experiments, it is demonstrated that our method can identify crucial structures in a target graph in various settings.