# MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks

arXiv: https://arxiv.org/abs/2104.08060 · HTML: https://mlsanity.com/paper/2104.08060/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 26 of 26)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [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)
- [A Fair Comparison of Graph Neural Networks for Graph Classification](https://mlsanity.com/paper/1912.09893/) (2019)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)
- [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)
- [Optimization of Molecules via Deep Reinforcement Learning](https://mlsanity.com/paper/1810.08678/) (2018)
- [Deep Reinforcement Learning for De-Novo Drug Design](https://mlsanity.com/paper/1711.10907/) (2017)
- [Explainability Techniques for Graph Convolutional Networks](https://mlsanity.com/paper/1905.13686/) (2019)
- [A Gentle Introduction to Deep Learning for Graphs](https://mlsanity.com/paper/1912.12693/) (2019)
- [RelEx: A Model-Agnostic Relational Model Explainer](https://mlsanity.com/paper/2006.00305/) (2020)
- [A Deep Generative Model for Fragment-Based Molecule Generation](https://mlsanity.com/paper/2002.12826/) (2020)
- [Contrastive Graph Neural Network Explanation](https://mlsanity.com/paper/2010.13663/) (2020)
- [Edge-based sequential graph generation with recurrent neural networks](https://mlsanity.com/paper/2002.00102/) (2020)
- [Fast Real-time Counterfactual Explanations](https://mlsanity.com/paper/2007.05684/) (2020)

## Built on by (most cited first, 30 of 32)

- [Robust Counterfactual Explanations on Graph Neural Networks](https://mlsanity.com/paper/2107.04086/) (2021)
- [CLEAR: Generative Counterfactual Explanations on Graphs](https://mlsanity.com/paper/2210.08443/) (2022)
- [A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges](https://mlsanity.com/paper/2210.12089/) (2022)
- [A Survey on Explainability of Graph Neural Networks](https://mlsanity.com/paper/2306.01958/) (2023)
- [Counterfactual Learning on Graphs: A Survey](https://mlsanity.com/paper/2304.01391/) (2023)
- [A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection](https://mlsanity.com/paper/2205.10014/) (2022)
- [Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction](https://mlsanity.com/paper/2107.04119/) (2021)
- [Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation](https://mlsanity.com/paper/2404.15687/) (2024)
- [Probing Graph Representations](https://mlsanity.com/paper/2303.03951/) (2023)
- [Robust Stochastic Graph Generator for Counterfactual Explanations](https://mlsanity.com/paper/2312.11747/) (2023)
- [Recent Advances in Malware Detection: Graph Learning and Explainability](https://mlsanity.com/paper/2502.10556/) (2025)
- [GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation](https://mlsanity.com/paper/2206.02957/) (2022)
- [When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlook](https://mlsanity.com/paper/2312.12477/) (2023)
- [Improving the interpretability of GNN predictions through conformal-based graph sparsification](https://mlsanity.com/paper/2404.12356/) (2024)
- [Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference](https://mlsanity.com/paper/2406.13724/) (2024)
- [FragNet: A Graph Neural Network for Molecular Property Prediction with Four Levels of Interpretability](https://mlsanity.com/paper/2410.12156/) (2024)
- [Game-theoretic Counterfactual Explanation for Graph Neural Networks](https://mlsanity.com/paper/2402.06030/) (2024)
- [Graph Inverse Style Transfer for Counterfactual Explainability](https://mlsanity.com/paper/2505.17542/) (2025)
- [Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapes](https://mlsanity.com/paper/2308.02353/) (2023)
- [Counterfactual Reasoning with Knowledge Graph Embeddings](https://mlsanity.com/paper/2403.06936/) (2024)
- [Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning](https://mlsanity.com/paper/2406.13869/) (2024)
- [From Text to Graph: Leveraging Graph Neural Networks for Enhanced Explainability in NLP](https://mlsanity.com/paper/2504.02064/) (2025)
- [Improving Counterfactual Truthfulness for Molecular Property Prediction through Uncertainty Quantification](https://mlsanity.com/paper/2504.02606/) (2025)
- [Finding Counterfactual Evidences for Node Classification](https://mlsanity.com/paper/2505.11396/) (2025)
- [Beyond Edge Deletion: A Comprehensive Approach to Counterfactual Explanation in Graph Neural Networks](https://mlsanity.com/paper/2603.04209/) (2026)
- [Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversion](https://mlsanity.com/paper/2608.12083/) (2026)
- [Global Graph Counterfactual Explanation: A Subgraph Mapping Approach](https://mlsanity.com/paper/2410.19978/) (2024)
- [Enhancing Chemical Explainability Through Counterfactual Masking](https://mlsanity.com/paper/2508.18561/) (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)
- [A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networks](https://mlsanity.com/paper/2606.22033/) (2026)

## Abstract (arXiv)

Explainable AI (XAI) is a research area whose objective is to increase trustworthiness and to enlighten the hidden mechanism of opaque machine learning techniques. This becomes increasingly important in case such models are applied to the chemistry domain, for its potential impact on humans' health, e.g, toxicity analysis in pharmacology. In this paper, we present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction t asks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations for a specific prediction under the form of (valid) compounds with high structural similarity and different predicted properties. Given a trained DGN, we train a reinforcement learning based generator to output counterfactual explanations. At each step, MEG feeds the current candidate counterfactual into the DGN, collects the prediction and uses it to reward the RL agent to guide the exploration. Furthermore, we restrict the action space of the agent in order to only keep actions that maintain the molecule in a valid state. We discuss the results showing how the model can convey non-ML experts with key insights into the learning model focus in the neighbourhood of a molecule.