GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks

Recently, graph neural networks (GNN) were shown to be successful in effectively representing graph structured data because of their good performance and generalization ability. However, explaining the effectiveness of GNN models is a challenging task because of the complex nonlinear transformations made over the iterations. In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method. GraphLIME is a generic GNN-model explanation framework that learns a nonlinear interpretable model locally in the subgraph of the node being explained. Through experiments on two real-world datasets, the explanations of GraphLIME are found to be of extraordinary degree and more descriptive in comparison to the existing explanation methods.

[1]  Fragkiskos D. Malliaros,et al.  GraphSVX: Shapley Value Explanations for Graph Neural Networks , 2021, ECML/PKDD.

[2]  Jure Leskovec,et al.  OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs , 2021, NeurIPS Datasets and Benchmarks.

[3]  Shuiwang Ji,et al.  On Explainability of Graph Neural Networks via Subgraph Explorations , 2021, ICML.

[4]  Bo Zong,et al.  Parameterized Explainer for Graph Neural Network , 2020, NeurIPS.

[5]  Arti Ramesh,et al.  RelEx: A Model-Agnostic Relational Model Explainer , 2020, AIES.

[6]  Fernando Gama,et al.  Stability Properties of Graph Neural Networks , 2019, IEEE Transactions on Signal Processing.

[7]  J. Leskovec,et al.  GNNExplainer: Generating Explanations for Graph Neural Networks , 2019, NeurIPS.

[8]  Samuel Kaski,et al.  Block HSIC Lasso: model-free biomarker detection for ultra-high dimensional data , 2019, bioRxiv.

[9]  Pradeep Ravikumar,et al.  Representer Point Selection for Explaining Deep Neural Networks , 2018, NeurIPS.

[10]  Been Kim,et al.  Sanity Checks for Saliency Maps , 2018, NeurIPS.

[11]  Ryan A. Rossi,et al.  Graph Classification using Structural Attention , 2018, KDD.

[12]  Qiang Ma,et al.  Dual Graph Convolutional Networks for Graph-Based Semi-Supervised Classification , 2018, WWW.

[13]  Hao Ma,et al.  GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs , 2018, UAI.

[14]  Le Song,et al.  Learning to Explain: An Information-Theoretic Perspective on Model Interpretation , 2018, ICML.

[15]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[16]  Le Song,et al.  Stochastic Training of Graph Convolutional Networks with Variance Reduction , 2017, ICML.

[17]  Jun Zhu,et al.  Stochastic Training of Graph Convolutional Networks , 2017, ICML 2018.

[18]  Jure Leskovec,et al.  Interpretable & Explorable Approximations of Black Box Models , 2017, ArXiv.

[19]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[20]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[21]  Yurong Liu,et al.  A survey of deep neural network architectures and their applications , 2017, Neurocomputing.

[22]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[23]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

[24]  Ankur Taly,et al.  Axiomatic Attribution for Deep Networks , 2017, ICML.

[25]  Eneldo Loza Mencía,et al.  DeepRED - Rule Extraction from Deep Neural Networks , 2016, DS.

[26]  Avishek Saha,et al.  Ultra High-Dimensional Nonlinear Feature Selection for Big Biological Data , 2016, IEEE Transactions on Knowledge and Data Engineering.

[27]  Marco Tulio Ribeiro,et al.  “Why Should I Trust You?”: Explaining the Predictions of Any Classifier , 2016, NAACL.

[28]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[29]  Foster J. Provost,et al.  Explaining Data-Driven Document Classifications , 2013, MIS Q..

[30]  Masashi Sugiyama,et al.  High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso , 2012, Neural Computation.

[31]  Bernhard Schölkopf,et al.  Measuring Statistical Dependence with Hilbert-Schmidt Norms , 2005, ALT.

[32]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Madhuri Jha.  ANN-DT : An Algorithm for Extraction of Decision Trees from Artificial Neural Networks , 2013 .

[34]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[35]  Pascal Vincent,et al.  Visualizing Higher-Layer Features of a Deep Network , 2009 .

[36]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.