# Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction

arXiv: https://arxiv.org/abs/2107.04119 · HTML: https://mlsanity.com/paper/2107.04119/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 68 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (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)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [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)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [Constrained Graph Variational Autoencoders for Molecule Design](https://mlsanity.com/paper/1805.09076/) (2018)
- [Graph Information Bottleneck for Subgraph Recognition](https://mlsanity.com/paper/2010.05563/) (2020)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [RetroXpert: Decompose Retrosynthesis Prediction like a Chemist](https://mlsanity.com/paper/2011.02893/) (2020)
- [Understanding Random Forests: From Theory to Practice](https://mlsanity.com/paper/1407.7502/) (2014)
- [Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network](https://mlsanity.com/paper/2003.02944/) (2020)

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

- [A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection](https://mlsanity.com/paper/2205.10014/) (2022)
- [Towards Faithful and Consistent Explanations for Graph Neural Networks](https://mlsanity.com/paper/2205.13733/) (2022)
- [Graph Neural Networks in Modern AI-aided Drug Discovery](https://mlsanity.com/paper/2506.06915/) (2025)
- [Towards Explainable Motion Prediction using Heterogeneous Graph Representations](https://mlsanity.com/paper/2212.03806/) (2022)
- [Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment](https://mlsanity.com/paper/2301.02791/) (2023)
- [Knowledge-augmented Graph Machine Learning for Drug Discovery: A Survey](https://mlsanity.com/paper/2302.08261/) (2023)
- [Explainable Artificial Intelligence for Drug Discovery and Development -- A Comprehensive Survey](https://mlsanity.com/paper/2309.12177/) (2023)
- [MTPNet: Multi-Grained Target Perception for Unified Activity Cliff Prediction](https://mlsanity.com/paper/2506.05427/) (2025)
- [A Semi-supervised Molecular Learning Framework for Activity Cliff Estimation](https://mlsanity.com/paper/2601.04507/) (2026)
- [Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization](https://mlsanity.com/paper/2507.03318/) (2025)
- [Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Graph Neural Networks](https://mlsanity.com/paper/2402.04710/) (2024)
- [Rotational Sampling: A Plug-and-Play Encoder for Rotation-Invariant 3D Molecular GNNs](https://mlsanity.com/paper/2507.01073/) (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)
- [Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It](https://mlsanity.com/paper/2605.07527/) (2026)
- [MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions](https://mlsanity.com/paper/2608.30636/) (2026)

## Abstract (arXiv)

Advances in machine learning have led to graph neural network-based methods for drug discovery, yielding promising results in molecular design, chemical synthesis planning, and molecular property prediction. However, current graph neural networks (GNNs) remain of limited acceptance in drug discovery is limited due to their lack of interpretability. Although this major weakness has been mitigated by the development of explainable artificial intelligence (XAI) techniques, the "ground truth" assignment in most explainable tasks ultimately rests with subjective judgments by humans so that the quality of model interpretation is hard to evaluate in quantity. In this work, we first build three levels of benchmark datasets to quantitatively assess the interpretability of the state-of-the-art GNN models. Then we implemented recent XAI methods in combination with different GNN algorithms to highlight the benefits, limitations, and future opportunities for drug discovery. As a result, GradInput and IG generally provide the best model interpretability for GNNs, especially when combined with GraphNet and CMPNN. The integrated and developed XAI package is fully open-sourced and can be used by practitioners to train new models on other drug discovery tasks.