PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks

By Minh N. Vu, My T. Thai. Neural Information Processing Systems, 2020

427 citations recorded by the source corpus.

In Graph Neural Networks (GNNs), the graph structure is incorporated into the learning of node representations. This complex structure makes explaining GNNs' predictions become much more challenging. In this paper, we propose PGM-Explainer, a Probabilistic Graphical Model (PGM) model-agnostic explainer for GNNs. Given a prediction to be explained, PGM-Explainer identifies crucial graph components and generates an explanation in form of a PGM approximating that prediction. Different from existing explainers for GNNs where the explanations are drawn from a set of linear functions of explained features, PGM-Explainer is able to demonstrate the dependencies of explained features in form of conditional probabilities. Our theoretical analysis shows that the PGM generated by PGM-Explainer includes the Markov-blanket of the target prediction, i.e. including all its statistical information. We also show that the explanation returned by PGM-Explainer contains the same set of independence statements in the perfect map. Our experiments on both synthetic and real-world datasets show that PGM-Explainer achieves better performance than existing explainers in many benchmark tasks.

Subfields: Artificial Intelligence, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/a8ae2d8232db04d88cf622e5fabd11da3163aa8f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Materials Chemistry

Citations in the corpus

Finding Global Homophily in Graph Neural Networks When Meeting Heterophily (2022, background): “Further, GNNs have been widely studied from various perspectives, such as the over-smoothing problem (Zhao & Akoglu, 2019; Rong et al., 2019), the adversarial attack and defense (Dai et al., 2018; Zhu et al., 2019), and the model explainability (Vu & Thai, 2020; Shan et al., 2021).”
Higher-Order Explanations of Graph Neural Networks via Relevant Walks (2020, background): “PGMExplainer [29] learns a probabilistic graphicalmodel from the network, which is then able to measure the probability for different higher order feature interactions in the model.”
Explainable AI Methods - A Brief Overview (2020, result): “…would be beneﬁcial - and is considered future work - if GraphLIME was also trying to ﬁnd important graph substructures instead of just features, if it was compared with other methods like PGExplainer [52], PG-MExplainer [83], GNN-LRP [72], and if it were extended to multiple instance explanations.”
Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism (2022, methodology): “Other methods including PGM-Explainer (Vu & Thai, 2020) leveraging graphical models, Gem (Lin et al., 2021) checking Granger causality and Graphlime (Huang et al., 2020) using HSIC Lasso are only applied to node-level task interpretation.”
On Explainability of Graph Neural Networks via Subgraph Explorations (2021, methodology): “While several recent studies have developed GNN explanation methods, such as GNNExplainer (Ying et al., 2019), PGExplainer (Luo et al., 2020), and PGM-Explainer (Vu & Thai, 2020), they invariably focus on explainability at node, edge, or node feature levels, and only consider subgraphs indirectly vi”
Explainability in Graph Neural Networks: A Taxonomic Survey (2020, methodology): “The other methods only need the forward computations of the trained GNNs. TABLE 1 A Comprehensive Analysis of Different Explanation Methods Method TYPE LEARNING TASK TARGET BLACK-BOX FLOW DESIGN SA [54], [55] Instance-level ✗ GC/NC N/E/NF ✗ Backward ✗ Guided BP [54] Instance-level ✗ GC/NC N/E/NF ✗ B”