GNES: Learning to Explain Graph Neural Networks

Gao, Yuyang; Sun, Tanfeng; Bhatt, Rishab; Yu, Dazhou; Hong, Sung‐Soo; Zhao, Liang

doi:10.1109/icdm51629.2021.00023

Cited by 27 publications

(29 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GNNExplainer approach is also edge-centric, but applied to identify the subgraph for an object determining its prediction ( Ying et al., 2019 ). In addition to GNNExplainer, a method termed GNN Explanation Supervision has been reported that combines node- and edge-based model explanation through graph regularization techniques, aiming to achieve consistency between node- and edge-based explanations through supervised adaptive learning ( Gao et al., 2021 ). For graph convolutional networks (GCNs), edges important for model decisions have also been identified using previously introduced agnostic local explanation models ( Kasanishi et al., 2021 ).…”

Section: Resultsmentioning

confidence: 99%

EdgeSHAPer: Bond-centric Shapley value-based explanation method for graph neural networks

et al. 2022

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

EdgeSHAPer: Bond-centric Shapley value-based explanation method for graph neural networks

et al. 2022

View full text Add to dashboard Cite

“…194 with permission from the Royal Society of Chemistry), e explainable GNNs (adapted from ref. 311 ), f Crystal GNN to predict methane adsorption volumes in metal organic frameworks (MOFs) (this illustration was published in ref. 234 , Copyright Elsevier), doped structures (this illustration was published in ref.…”

Section: Applicationsmentioning

confidence: 99%

Graph neural networks for materials science and chemistry

et al. 2022

View full text Add to dashboard Cite

Machine learning plays an increasingly important role in many areas of chemistry and materials science, being used to predict materials properties, accelerate simulations, design new structures, and predict synthesis routes of new materials. Graph neural networks (GNNs) are one of the fastest growing classes of machine learning models. They are of particular relevance for chemistry and materials science, as they directly work on a graph or structural representation of molecules and materials and therefore have full access to all relevant information required to characterize materials. In this Review, we provide an overview of the basic principles of GNNs, widely used datasets, and state-of-the-art architectures, followed by a discussion of a wide range of recent applications of GNNs in chemistry and materials science, and concluding with a road-map for the further development and application of GNNs.

show abstract

“…Grad-CAM [143] generalizes it to the model-agnostic setting by using average class-wise gradients in place of linear classification parameters. It is straightforward to estimate importance weights of node attributes using these methods, and edges connecting important nodes would also be taken as important [60].…”

Section: Instance-levelmentioning

confidence: 99%

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

Dai¹,

Zhao²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have made rapid developments in the recent years. Due to their great ability in modeling graph-structured data, GNNs are vastly used in various applications, including high-stakes scenarios such as financial analysis, traffic predictions, and drug discovery. Despite their great potential in benefiting humans in the real world, recent study shows that GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data and lack interpretability, which have risk of causing unintentional harm to the users and society. For example, existing works demonstrate that attackers can fool the GNNs to give the outcome they desire with unnoticeable perturbation on training graph. GNNs trained on social networks may embed the discrimination in their decision process, strengthening the undesirable societal bias. Consequently, trustworthy GNNs in various aspects are emerging to prevent the harm from GNN models and increase the users' trust in GNNs. In this paper, we give a comprehensive survey of GNNs in the computational aspects of privacy, robustness, fairness, and explainability. For each aspect, we give the taxonomy of the related methods and formulate the general frameworks for the multiple categories of trustworthy GNNs. We also discuss the future research directions of each aspect and connections between these aspects to help achieve trustworthiness.

show abstract

GNES: Learning to Explain Graph Neural Networks

Cited by 27 publications

References 24 publications

EdgeSHAPer: Bond-centric Shapley value-based explanation method for graph neural networks

EdgeSHAPer: Bond-centric Shapley value-based explanation method for graph neural networks

Graph neural networks for materials science and chemistry

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

Contact Info

Product

Resources

About