Parameterized Explainer for Graph Neural Network

By Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, Xiang Zhang. Neural Information Processing Systems, 2020

824 citations recorded by the source corpus.

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method independently addresses the local explanations (i.e., important subgraph structure and node features) to interpret why a GNN model makes the prediction for a single instance, e.g. a node or a graph. As a result, the explanation generated is painstakingly customized for each instance. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to a lack of generalizability and hindering it from being used in the inductive setting. Besides, as it is designed for explaining a single instance, it is challenging to explain a set of instances naturally (e.g., graphs of a given class). In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which enables PGExplainer a natural approach to explaining multiple instances collectively. Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7\% relative improvement in AUC on explaining graph classification over the leading baseline.

Subfields: Artificial Intelligence, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/d9f5ec342df97e060b527a8bc18ae4e97401f246

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

Adversarial Graph Augmentation to Improve Graph Contrastive Learning (2021, methodology): “This style of edge dropping based on a random graph model has also been used for parameterized explanations of GNNs [58].”
Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond (2021, background): “Recently, more researches focus on the interpretations of GNN models, such as GraphLIME [76], CoGE [51], Counterfactual explanations on GNNs [18] and others [20, 111, 132].”
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): “Besides the models (Ying et al., 2019; Luo et al., 2020; Schlichtkrull et al., 2021; Yu et al., 2021) that we have compared with in detail in Sec.”
GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks (2020, methodology): “For example, [9] was proposed to utilize mutual information to find a subgraph with associated features for interpreting GNN models; PGExplainer [16] learns a parameterized model to predict whether an edge is important; SubgraphX [17] explains GNNs by exploring and identifying important subgraphs; G”
Discovering Invariant Rationales for Graph Neural Networks (2022, methodology): “The goal of selective rationalization ( aka. feature attribution) (Chang et al., 2020; Ying et al., 2019; Luo et al., 2020; Wang et al., 2021c) is to ﬁnd a small subset of the input’s graph features — rationale — which best guides or explains the model prediction.”
Higher-Order Explanations of Graph Neural Networks via Relevant Walks (2020, methodology): “05 to the previous baseline performance in [27].”
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection (2023, background): “Such understanding fosters trust in the system and enables the discovery of latent patterns within the data [293], [295].”
Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking (2020, methodology): “Concurrently to this paper, Luo et al. (2020) have also developed an interpretability technique for GNNs relying on differentiable edge masking.”
On Explainability of Graph Neural Networks via Subgraph Explorations (2021, methodology): “Meanwhile, PGExplainer (Luo et al., 2020) learns a parameterized model to predict whether an edge is important, which is trained using all edges in the dataset.”