# Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanations

arXiv: https://arxiv.org/abs/2403.07849 · HTML: https://mlsanity.com/paper/2403.07849/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 12 Mar 2024.

## Builds on (most cited first, 21 of 21)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [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)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017)
- [Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting](https://mlsanity.com/paper/2006.09252/) (2020)
- [The Surprising Power of Graph Neural Networks with Random Node Initialization](https://mlsanity.com/paper/2010.01179/) (2020)
- [Weisfeiler and Leman go Machine Learning: The Story so far](https://mlsanity.com/paper/2112.09992/) (2021)
- [Evaluating Explainability for Graph Neural Networks](https://mlsanity.com/paper/2208.09339/) (2022)
- [SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism](https://mlsanity.com/paper/2101.08170/) (2021)
- [Coloring graph neural networks for node disambiguation](https://mlsanity.com/paper/1912.06058/) (2019)
- [Graph Neural Networks with Local Graph Parameters](https://mlsanity.com/paper/2106.06707/) (2021)
- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods](https://mlsanity.com/paper/2106.09078/) (2021)
- [A Survey on Explainability of Graph Neural Networks](https://mlsanity.com/paper/2306.01958/) (2023)
- [Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs](https://mlsanity.com/paper/2206.09144/) (2022)
- [A Typology for Exploring the Mitigation of Shortcut Behavior](https://mlsanity.com/paper/2203.03668/) (2022)
- [The Intriguing Properties of Model Explanations](https://mlsanity.com/paper/1801.09808/) (2018)

## Built on by (most cited first, 3 of 3)

- [On the Feasibility of Fidelity^- for Graph Pruning](https://mlsanity.com/paper/2406.11504/) (2024)
- [Rule Based Learning with Dynamic (Graph) Neural Networks](https://mlsanity.com/paper/2406.09954/) (2024)
- [Invariant-Based Weight Sharing for Message Passing](https://mlsanity.com/paper/2605.25750/) (2026)

## Abstract (arXiv)

We formulate an XAI-based model improvement approach for Graph Neural Networks (GNNs) for node classification, called Explanation Enhanced Graph Learning (EEGL). The goal is to improve predictive performance of GNN using explanations. EEGL is an iterative self-improving algorithm, which starts with a learned "vanilla" GNN, and repeatedly uses frequent subgraph mining to find relevant patterns in explanation subgraphs. These patterns are then filtered further to obtain application-dependent features corresponding to the presence of certain subgraphs in the node neighborhoods. Giving an application-dependent algorithm for such a subgraph-based extension of the Weisfeiler-Leman (1-WL) algorithm has previously been posed as an open problem. We present experimental evidence, with synthetic and real-world data, which show that EEGL outperforms related approaches in predictive performance and that it has a node-distinguishing power beyond that of vanilla GNNs. We also analyze EEGL's training dynamics.