# A Meta-Learning Approach for Training Explainable Graph Neural Networks

arXiv: https://arxiv.org/abs/2109.09426 · HTML: https://mlsanity.com/paper/2109.09426/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 20 Sep 2021.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [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)
- [GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2001.06216/) (2020)
- [Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking](https://mlsanity.com/paper/2010.00577/) (2020)
- [CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2102.03322/) (2021)
- [A Gentle Introduction to Deep Learning for Graphs](https://mlsanity.com/paper/1912.12693/) (2019)
- [Generalized Inner Loop Meta-Learning](https://mlsanity.com/paper/1910.01727/) (2019)
- [Interpretable and Efficient Heterogeneous Graph Convolutional Network](https://mlsanity.com/paper/2005.13183/) (2020)
- [Adaptive Propagation Graph Convolutional Network](https://mlsanity.com/paper/2002.10306/) (2020)
- [Fast Haar Transforms for Graph Neural Networks](https://mlsanity.com/paper/1907.04786/) (2019)
- [Contrastive Graph Neural Network Explanation](https://mlsanity.com/paper/2010.13663/) (2020)
- [Medical Entity Disambiguation Using Graph Neural Networks](https://mlsanity.com/paper/2104.01488/) (2021)

## Built on by (most cited first, 15 of 15)

- [Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency](https://mlsanity.com/paper/2306.02109/) (2023)
- [Explaining the Explainers in Graph Neural Networks: a Comparative Study](https://mlsanity.com/paper/2210.15304/) (2022)
- [MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation](https://mlsanity.com/paper/2307.07832/) (2023)
- [How Interpretable Are Interpretable Graph Neural Networks?](https://mlsanity.com/paper/2406.07955/) (2024)
- [Towards Training GNNs using Explanation Directed Message Passing](https://mlsanity.com/paper/2211.16731/) (2022)
- [Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability](https://mlsanity.com/paper/2304.07152/) (2023)
- [xAI-Drop: Don't Use What You Cannot Explain](https://mlsanity.com/paper/2407.20067/) (2024)
- [Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression](https://mlsanity.com/paper/2209.13410/) (2022)
- [Generating Human Understandable Explanations for Node Embeddings](https://mlsanity.com/paper/2406.07642/) (2024)
- [Interpreting Temporal Graph Neural Networks with Koopman Theory](https://mlsanity.com/paper/2410.13469/) (2024)
- [Cluster-CAM: Cluster-Weighted Visual Interpretation of CNNs' Decision in Image Classification](https://mlsanity.com/paper/2302.01642/) (2023)
- [REVEAL-IT: REinforcement learning with Visibility of Evolving Agent poLicy for InTerpretability](https://mlsanity.com/paper/2406.14214/) (2024)
- [A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks](https://mlsanity.com/paper/2410.21006/) (2024)
- [MetaGMT: Improving Actionable Interpretability of Graph Multilinear Networks via Meta-Learning Filtration](https://mlsanity.com/paper/2505.19445/) (2025)
- [Enhancing Imbalanced Node Classification via Curriculum-Guided Feature Learning and Three-Stage Attention Network](https://mlsanity.com/paper/2602.03808/) (2026)

## Abstract (arXiv)

In this paper, we investigate the degree of explainability of graph neural networks (GNNs). Existing explainers work by finding global/local subgraphs to explain a prediction, but they are applied after a GNN has already been trained. Here, we propose a meta-learning framework for improving the level of explainability of a GNN directly at training time, by steering the optimization procedure towards what we call `interpretable minima'. Our framework (called MATE, MetA-Train to Explain) jointly trains a model to solve the original task, e.g., node classification, and to provide easily processable outputs for downstream algorithms that explain the model's decisions in a human-friendly way. In particular, we meta-train the model's parameters to quickly minimize the error of an instance-level GNNExplainer trained on-the-fly on randomly sampled nodes. The final internal representation relies upon a set of features that can be `better' understood by an explanation algorithm, e.g., another instance of GNNExplainer. Our model-agnostic approach can improve the explanations produced for different GNN architectures and use any instance-based explainer to drive this process. Experiments on synthetic and real-world datasets for node and graph classification show that we can produce models that are consistently easier to explain by different algorithms. Furthermore, this increase in explainability comes at no cost for the accuracy of the model.