# Encoding Concepts in Graph Neural Networks

arXiv: https://arxiv.org/abs/2207.13586 · HTML: https://mlsanity.com/paper/2207.13586/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 47 references that are in the map.
- First posted on arXiv 27 Jul 2022.

## Builds on (most cited first, 30 of 31)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [TUDataset: A collection of benchmark datasets for learning with graphs](https://mlsanity.com/paper/2007.08663/) (2020)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks](https://mlsanity.com/paper/1909.01315/) (2019)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [Concept Whitening for Interpretable Image Recognition](https://mlsanity.com/paper/2002.01650/) (2020)
- [PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2010.05788/) (2020)
- [CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2102.03322/) (2021)
- [PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest](https://mlsanity.com/paper/2007.03634/) (2020)
- [Robust Counterfactual Explanations on Graph Neural Networks](https://mlsanity.com/paper/2107.04086/) (2021)
- [Now You See Me (CME): Concept-based Model Extraction](https://mlsanity.com/paper/2010.13233/) (2020)
- [Entropy-based Logic Explanations of Neural Networks](https://mlsanity.com/paper/2106.06804/) (2021)
- [Logic Explained Networks](https://mlsanity.com/paper/2108.05149/) (2021)
- [GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks](https://mlsanity.com/paper/2107.11889/) (2021)
- [Trust in AI: Interpretability is not necessary or sufficient, while black-box interaction is necessary and sufficient](https://mlsanity.com/paper/2202.05302/) (2022)

## Built on by (most cited first, 18 of 18)

- [Global Explainability of GNNs via Logic Combination of Learned Concepts](https://mlsanity.com/paper/2210.07147/) (2022)
- [Interpretable Neural-Symbolic Concept Reasoning](https://mlsanity.com/paper/2304.14068/) (2023)
- [Learning to Receive Help: Intervention-Aware Concept Embedding Models](https://mlsanity.com/paper/2309.16928/) (2023)
- [Explaining the Explainers in Graph Neural Networks: a Comparative Study](https://mlsanity.com/paper/2210.15304/) (2022)
- [Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs](https://mlsanity.com/paper/2406.15156/) (2024)
- [MEGAN: Multi-Explanation Graph Attention Network](https://mlsanity.com/paper/2211.13236/) (2022)
- [GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data](https://mlsanity.com/paper/2211.06302/) (2022)
- [SHARCS: Shared Concept Space for Explainable Multimodal Learning](https://mlsanity.com/paper/2307.00316/) (2023)
- [Interpretable Graph Networks Formulate Universal Algebra Conjectures](https://mlsanity.com/paper/2307.11688/) (2023)
- [Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts](https://mlsanity.com/paper/2311.15112/) (2023)
- [Global Concept Explanations for Graphs by Contrastive Learning](https://mlsanity.com/paper/2404.16532/) (2024)
- [Automated Molecular Concept Generation and Labeling with Large Language Models](https://mlsanity.com/paper/2406.09612/) (2024)
- [Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies](https://mlsanity.com/paper/2305.15961/) (2023)
- [Digital Histopathology with Graph Neural Networks: Concepts and Explanations for Clinicians](https://mlsanity.com/paper/2312.02225/) (2023)
- [Disentangled and Self-Explainable Node Representation Learning](https://mlsanity.com/paper/2410.21043/) (2024)
- [GCI: A (G)raph (C)oncept (I)nterpretation Framework](https://mlsanity.com/paper/2302.04899/) (2023)
- [Combating Spurious Correlations in Graph Interpretability via Self-Reflection](https://mlsanity.com/paper/2601.11021/) (2026)
- [Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning](https://mlsanity.com/paper/2604.11986/) (2026)

## Abstract (arXiv)

The opaque reasoning of Graph Neural Networks induces a lack of human trust. Existing graph network explainers attempt to address this issue by providing post-hoc explanations, however, they fail to make the model itself more interpretable. To fill this gap, we introduce the Concept Encoder Module, the first differentiable concept-discovery approach for graph networks. The proposed approach makes graph networks explainable by design by first discovering graph concepts and then using these to solve the task. Our results demonstrate that this approach allows graph networks to: (i) attain model accuracy comparable with their equivalent vanilla versions, (ii) discover meaningful concepts that achieve high concept completeness and purity scores, (iii) provide high-quality concept-based logic explanations for their prediction, and (iv) support effective interventions at test time: these can increase human trust as well as significantly improve model performance.