Evaluating Explainability for Graph Neural Networks

• URL: http://arxiv.org/abs/2208.09339v1
• Date: Fri, 19 Aug 2022 13:43:52 GMT
• Title: Evaluating Explainability for Graph Neural Networks
• Authors: Chirag Agarwal, Owen Queen, Himabindu Lakkaraju, Marinka Zitnik
• Abstract summary: We introduce a synthetic graph data generator, ShapeGGen, which can generate a variety of benchmark datasets. We include ShapeGGen and several real-world graph datasets into an open-source graph explainability library, GraphXAI.
• Score: 21.339111121529815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As post hoc explanations are increasingly used to understand the behavior of graph neural networks (GNNs), it becomes crucial to evaluate the quality and reliability of GNN explanations. However, assessing the quality of GNN explanations is challenging as existing graph datasets have no or unreliable ground-truth explanations for a given task. Here, we introduce a synthetic graph data generator, ShapeGGen, which can generate a variety of benchmark datasets (e.g., varying graph sizes, degree distributions, homophilic vs. heterophilic graphs) accompanied by ground-truth explanations. Further, the flexibility to generate diverse synthetic datasets and corresponding ground-truth explanations allows us to mimic the data generated by various real-world applications. We include ShapeGGen and several real-world graph datasets into an open-source graph explainability library, GraphXAI. In addition to synthetic and real-world graph datasets with ground-truth explanations, GraphXAI provides data loaders, data processing functions, visualizers, GNN model implementations, and evaluation metrics to benchmark the performance of GNN explainability methods.

Related papers

• Graph Reasoning Networks [9.18586425686959]
  Graph Reasoning Networks (GRNs) is a novel approach to combine the strengths of fixed and learned graph representations and a reasoning module based on a differentiable satisfiability solver. Results on real-world datasets show comparable performance to GNNs. Experiments on synthetic datasets demonstrate the potential of the newly proposed method.
  arXiv  Detail & Related papers  (2024-07-08T10:53:49Z)
• DGNN: Decoupled Graph Neural Networks with Structural Consistency between Attribute and Graph Embedding Representations [62.04558318166396]
  Graph neural networks (GNNs) demonstrate a robust capability for representation learning on graphs with complex structures. A novel GNNs framework, dubbed Decoupled Graph Neural Networks (DGNN), is introduced to obtain a more comprehensive embedding representation of nodes. Experimental results conducted on several graph benchmark datasets verify DGNN's superiority in node classification task.
  arXiv  Detail & Related papers  (2024-01-28T06:43:13Z)
• Graph Distillation with Eigenbasis Matching [43.59076214528843]
  We propose Graph Distillation with Eigenbasis Matching (GDEM) to replace the real large graph. GDEM aligns the eigenbasis and node features of real and synthetic graphs. It directly replicates the spectrum of the real graph and thus prevents the influence of GNNs.
  arXiv  Detail & Related papers  (2023-10-13T15:48:12Z)
• 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)
• Graph Generative Model for Benchmarking Graph Neural Networks [73.11514658000547]
  We introduce a novel graph generative model that learns and reproduces the distribution of real-world graphs in a privacy-controlled way. Our model can successfully generate privacy-controlled, synthetic substitutes of large-scale real-world graphs that can be effectively used to benchmark GNN models.
  arXiv  Detail & Related papers  (2022-07-10T06:42:02Z)
• GraphSVX: Shapley Value Explanations for Graph Neural Networks [81.83769974301995]
  Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data. In this paper, we propose a unified framework satisfied by most existing GNN explainers. We introduce GraphSVX, a post hoc local model-agnostic explanation method specifically designed for GNNs.
  arXiv  Detail & Related papers  (2021-04-18T10:40:37Z)
• XGNN: Towards Model-Level Explanations of Graph Neural Networks [113.51160387804484]
  Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information. GNNs are mostly treated as black-boxes and lack human intelligible explanations. We propose a novel approach, known as XGNN, to interpret GNNs at the model-level.
  arXiv  Detail & Related papers  (2020-06-03T23:52:43Z)
• Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks [183.97265247061847]
  We leverage graph signal processing to characterize the representation space of graph neural networks (GNNs) We discuss the role of graph convolutional filters in GNNs and show that any architecture built with such filters has the fundamental properties of permutation equivariance and stability to changes in the topology. We also study the use of GNNs in recommender systems and learning decentralized controllers for robot swarms.
  arXiv  Detail & Related papers  (2020-03-08T13:02:15Z)
• Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification [15.41200827860072]
  We propose new graph features' explanation methods to identify the informative components and important node features. Our results demonstrate that our explanation approach can mimic data patterns used for node classification by human interpretation.
  arXiv  Detail & Related papers  (2020-02-02T23:53:21Z)
• GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks [45.824642013383944]
  Graph neural networks (GNN) were shown to be successful in effectively representing graph structured data. We propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso.
  arXiv  Detail & Related papers  (2020-01-17T09:50:28Z)

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.