EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time

• URL: http://arxiv.org/abs/2405.01762v2
• Date: Thu, 16 May 2024 14:55:47 GMT
• Title: EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time
• Authors: Shengyao Lu, Bang Liu, Keith G. Mills, Jiao He, Di Niu,
• Abstract summary: Most existing subgraph-level explainers face efficiency challenges in explaining Graph Neural Networks (GNNs) due to complex search processes. In this paper, we reveal that inducing subgraph explanations by edges is more comprehensive than other subgraph inducing techniques. We employ an efficient linear-time search algorithm over the edge-induced subgraphs, where the edges are ranked by an enhanced gradient-based importance.
• Score: 30.44473492282072
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding and explaining the predictions of Graph Neural Networks (GNNs), is crucial for enhancing their safety and trustworthiness. Subgraph-level explanations are gaining attention for their intuitive appeal. However, most existing subgraph-level explainers face efficiency challenges in explaining GNNs due to complex search processes. The key challenge is to find a balance between intuitiveness and efficiency while ensuring transparency. Additionally, these explainers usually induce subgraphs by nodes, which may introduce less-intuitive disconnected nodes in the subgraph-level explanations or omit many important subgraph structures. In this paper, we reveal that inducing subgraph explanations by edges is more comprehensive than other subgraph inducing techniques. We also emphasize the need of determining the subgraph explanation size for each data instance, as different data instances may involve different important substructures. Building upon these considerations, we introduce a training-free approach, named EiG-Search. We employ an efficient linear-time search algorithm over the edge-induced subgraphs, where the edges are ranked by an enhanced gradient-based importance. We conduct extensive experiments on a total of seven datasets, demonstrating its superior performance and efficiency both quantitatively and qualitatively over the leading baselines.

Related papers

• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization [30.86182962089487]
  Graph Neural Networks (GNNs) have emerged as a powerful category of learning architecture for handling graph-structured data. We propose a dedicated plug-and-play normalization scheme, termed as SUbgraph-sPEcific FactoR Embedded Normalization (SuperNorm)
  arXiv  Detail & Related papers  (2023-05-31T14:37:31Z)
• DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
  We propose DEGREE to provide a faithful explanation for GNN predictions. By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction. We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
  arXiv  Detail & Related papers  (2023-05-22T10:29:52Z)
• Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching [68.35685422301613]
  We propose a novel non-parametric subgraph matching framework, dubbed MatchExplainer, to explore explanatory subgraphs. It couples the target graph with other counterpart instances and identifies the most crucial joint substructure by minimizing the node corresponding-based distance. Experiments on synthetic and real-world datasets show the effectiveness of our MatchExplainer by outperforming all state-of-the-art parametric baselines with significant margins.
  arXiv  Detail & Related papers  (2023-01-07T05:14:45Z)
• Faithful Explanations for Deep Graph Models [44.3056871040946]
  This paper studies faithful explanations for Graph Neural Networks (GNNs) It applies to existing explanation methods, including feature attributions and subgraph explanations. Third, we introduce emphk-hop Explanation with a Convolutional Core (KEC), a new explanation method that provably maximizes faithfulness to the original GNN.
  arXiv  Detail & Related papers  (2022-05-24T07:18:56Z)
• MotifExplainer: a Motif-based Graph Neural Network Explainer [19.64574177805823]
  We propose a novel method to explain Graph Neural Networks (GNNs) by identifying important motifs, recurrent and statistically significant patterns in graphs. Our proposed motif-based methods can provide better human-understandable explanations than methods based on nodes, edges, and regular subgraphs.
  arXiv  Detail & Related papers  (2022-02-01T16:11:21Z)
• On Explainability of Graph Neural Networks via Subgraph Explorations [48.56936527708657]
  We propose a novel method, known as SubgraphX, to explain graph neural networks (GNNs) Our work represents the first attempt to explain GNNs via identifying subgraphs explicitly.
  arXiv  Detail & Related papers  (2021-02-09T22:12:26Z)
• Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
  Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole. We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
  arXiv  Detail & Related papers  (2021-01-16T16:18:43Z)
• Parameterized Explainer for Graph Neural Network [49.79917262156429]
  We propose PGExplainer, a parameterized explainer for Graph Neural Networks (GNNs) 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.
  arXiv  Detail & Related papers  (2020-11-09T17:15:03Z)
• Subgraph Neural Networks [14.222887950206662]
  We introduce SubGNN, a subgraph neural network to learn disentangled subgraph representations. SubGNN performs exceptionally well on challenging biomedical datasets.
  arXiv  Detail & Related papers  (2020-06-18T13:54:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.