Explainability in Graph Neural Networks: A Taxonomic Survey

Yuan, Hao; Yu, Haiyang; Gui, Shurui; Ji, Shuiwang

doi:10.1109/tpami.2022.3204236

Cited by 206 publications

(153 citation statements)

References 55 publications

Supporting

Mentioning

152

Contrasting

Unclassified

Order By: Relevance

“…There have been only limited works studying the explainability of GNNs. In contrast to CNN-based approaches where explanations are usually provided at pixel-level [85], for graph data the focus is on the structural information, i.e., the identification of the salient nodes and/or edges contributing the most to the GNN classification decision [86]. In the following, we briefly survey techniques most relevant to ours, i.e., targeting graph classification tasks and providing nodelevel (rather than edge-level) explanations.…”

Section: B Gnn Decision Explanationmentioning

confidence: 99%

“…In the following, we briefly survey techniques most relevant to ours, i.e., targeting graph classification tasks and providing nodelevel (rather than edge-level) explanations. For a broader survey of various works on explainability the interested reader is referred to [86]. In [87], for each test instance the so-called GNNExplainer maximizes the mutual information between the GNN's prediction and a set of generated subgraph structures to learn a soft mask for selecting the nodes explaining the model's outcome.…”

Section: B Gnn Decision Explanationmentioning

confidence: 99%

See 1 more Smart Citation

ViGAT: Bottom-Up Event Recognition and Explanation in Video Using Factorized Graph Attention Network

2022

View full text Add to dashboard Cite

In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features for the task of event recognition and explanation in video, is proposed. The ViGAT head consists of graph attention network (GAT) blocks factorized along the spatial and temporal dimensions in order to capture effectively both local and long-term dependencies between objects or frames. Moreover, using the weighted in-degrees (WiDs) derived from the adjacency matrices at the various GAT blocks, we show that the proposed architecture can identify the most salient objects and frames that explain the decision of the network. A comprehensive evaluation study is performed, demonstrating that the proposed approach provides state-of-the-art results on three large, publicly available video datasets (FCVID, MiniKinetics, ActivityNet) a .a Source code and trained models will be made available upon acceptance.INDEX TERMS Video event recognition, eXplainable AI (XAI), graph attention network, factorized attention, bottom-up.

show abstract

Section: B Gnn Decision Explanationmentioning

confidence: 99%

Section: B Gnn Decision Explanationmentioning

confidence: 99%

ViGAT: Bottom-Up Event Recognition and Explanation in Video Using Factorized Graph Attention Network

2022

View full text Add to dashboard Cite

show abstract

“…Explanation methods for GNNs. Several GNN XAI approaches have been proposed, and a recent survey of the most relevant work is presented in [53].…”

Section: Related Workmentioning

confidence: 99%

GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations

Chen¹,

Silvestri²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, graph neural networks (GNNs) have been widely used to develop successful recommender systems. Although powerful, it is very difficult for a GNN-based recommender system to attach tangible explanations of why a specific item ends up in the list of suggestions for a given user. Indeed, explaining GNN-based recommendations is unique, and existing GNN explanation methods are inappropriate for two reasons. First, traditional GNN explanation methods are designed for node, edge, or graph classification tasks rather than ranking, as in recommender systems. Second, standard machine learning explanations are usually intended to support skilled decision-makers. Instead, recommendations are designed for any end-user, and thus their explanations should be provided in user-understandable ways.In this work, we propose GREASE, a novel method for explaining the suggestions provided by any black-box GNN-based recommender system. Specifically, GREASE first trains a surrogate model on a target useritem pair and its l-hop neighborhood. Then, it generates both factual and counterfactual explanations by finding optimal adjacency matrix perturbations to capture the sufficient and necessary conditions for an item to be recommended, respectively. Experimental results conducted on real-world datasets demonstrate that GREASE can generate concise and effective explanations for popular GNN-based recommender models.

show abstract

“…Since then, a multitude of instance-level explanation methods of GNNs has been proposed in the past few years. According to a recent survey [10], these instance-level explanation methods can be classified into four categories: gradient-based methods [26,27], perturbation-based methods [14,13,28], decomposition methods [26,27,29], and surrogate methods [15,30,31]. These four categories all attempt to explain how a GNN model makes such a prediction for a specific input instance.…”

Section: Related Workmentioning

confidence: 99%

“…However, the explainability of deep learning models on graphs is still less explored. Compared with explaining deep learning models on text or image data, explaining deep graph models is a more challenging task for several reasons [10]: (i) since a graph is not a grid-structured data like the image or text, the locality information of nodes is absent and each node has a varying number of neighbors [11], (ii) the adjacency matrix representing the topological information has only discrete values, which cannot be directly optimized via gradient-based methods [12], and (iii) graph data structure is heterogeneous in nature with different types of node features and edge features, which makes developing a one-sizefits-all explanation method for GNNs to be even more challenging.…”

Section: Introductionmentioning

confidence: 99%

GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks

Wang¹,

Shen²

2022

Preprint

View full text Add to dashboard Cite

Recently, Graph Neural Networks (GNNs) have significantly advanced the performance of machine learning tasks on graphs. However, this technological breakthrough makes people wonder: how does a GNN make such decisions, and can we trust its prediction with high confidence? When it comes to some critical fields such as biomedicine, where making wrong decisions can have severe consequences, interpreting the inner working mechanisms of GNNs before applying them is crucial. In this paper, we propose a novel model-agnostic model-level explanation method for different GNNs that follow the message passing scheme, GNNInterpreter, to explain the high-level decision-making process of the GNN model. More specifically, with continuous relaxation of graphs and the reparameterization trick, GNNInterpreter learns a probabilistic generative graph distribution which produces the most representative graph for the target prediction in the eye of the GNN model. Compared with the only existing work, GNNInterpreter is more computationally efficient and more flexible in generating explanation graphs with different types of node features and edge features, without introducing another blackbox to explain the GNN and without requiring domain-specific knowledge. Additionally, the experimental studies conducted on four different datasets demonstrate that the explanation graph generated by GNNInterpreter can match the desired graph pattern when the model is ideal and reveal potential model pitfalls if there exist any.Preprint. Under review.

show abstract

Explainability in Graph Neural Networks: A Taxonomic Survey

Cited by 206 publications

References 55 publications

ViGAT: Bottom-Up Event Recognition and Explanation in Video Using Factorized Graph Attention Network

ViGAT: Bottom-Up Event Recognition and Explanation in Video Using Factorized Graph Attention Network

GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations

GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks

Contact Info

Product

Resources

About