Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Non-exhaustive Learning Using Gaussian Mixture Generative Adversarial Networks Read chapter Read first chapter

2021 | OriginalPaper | Chapter

GraphSVX: Shapley Value Explanations for Graph Neural Networks

Authors : Alexandre Duval, Fragkiskos D. Malliaros

Published in: Machine Learning and Knowledge Discovery in Databases. Research Track

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data due to the incorporation of graph structure into the learning of node representations, which renders their comprehension challenging. In this paper, we first propose a unified framework satisfied by most existing GNN explainers. Then, we introduce GraphSVX, a post hoc local model-agnostic explanation method specifically designed for GNNs. GraphSVX is a decomposition technique that captures the “fair” contribution of each feature and node towards the explained prediction by constructing a surrogate model on a perturbed dataset. It extends to graphs and ultimately provides as explanation the Shapley Values from game theory. Experiments on real-world and synthetic datasets demonstrate that GraphSVX achieves state-of-the-art performance compared to baseline models while presenting core theoretical and human-centric properties.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter Inter-domain Multi-relational Link Prediction
next chapter Multi-view Self-supervised Heterogeneous Graph Embedding
Footnotes
1
Axiom: If \(\forall S \in \mathcal {P}(\{1,\ldots ,p\}) \text { and } j \notin S\), \({\textit{val}}(S\cup \{j\}) = {\textit{val}}(S)\), \(\text { then } \phi _j({\textit{val}}) = 0\).
 
Literature
1.
Backstrom, L., Leskovec, J.: Supervised random walks: predicting and recommending links in social networks. In: WSDM (2011)
2.
Baldassarre, F., Azizpour, H.: Explainability techniques for graph convolutional networks. arXiv (2019)
3.
Battaglia, P.W., Hamrick, J.B., Bapst, V., Sanchez-Gonzalez, A., et al.: Relational inductive biases, deep learning, and graph networks. arXiv (2018)
4.
Burkart, N., Huber, M.F.: A survey on the explainability of supervised machine learning. JAIR 70, 245–317 (2021)
5.
Dabkowski, P., Gal, Y.: Real time image saliency for black box classifiers. In: NeurIPS (2017)
6.
Datta, A., Sen, S., Zick, Y.: Algorithmic transparency via quantitative input influence: theory and experiments with learning systems. In: IEEE Symposium on Security and Privacy (SP) (2016)
7.
Debnath, K., et al.: Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity. J. Med. Chem. 34(2), 786–797 (1991)
8.
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: NeurIPS (2016)
9.
10.
Duvenaud, D., et al.: Convolutional networks on graphs for learning molecular fingerprints. In: NeurIPS (2015)
11.
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NeurIPS (2017)
12.
Huang, Q., Yamada, M., Tian, Y., Singh, D., Yin, D., Chang, Y.: GraphLIME: local interpretable model explanations for graph neural networks. arXiv (2020)
13.
Lipovetsky, S., Conklin, M.: Analysis of regression in game theory approach. ASMBI 17(4), 319–330 (2001)
14.
Lipton, P.: Contrastive explanation. Roy. Inst. Philos. Suppl. 27, 247–266 (1990)
15.
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: NeurIPS (2017)
16.
Luo, D., et al.: Parameterized explainer for graph neural network. In: NeurIPS (2020)
17.
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
18.
Miller, T., Howe, P., Sonenberg, L.: Explainable AI: beware of inmates running the asylum or: How I learnt to stop worrying and love the social and behavioural sciences. arXiv (2017)
19.
20.
O’neil, C.: Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy. Broadway Books (2016)
21.
Pope, P.E., Kolouri, S., Rostami, M., Martin, C.E., Hoffmann, H.: Explainability methods for graph convolutional neural networks. In: CVPR (2019)
22.
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you? Explaining the predictions of any classifier. In: KDD (2016)
23.
24.
25.
Saltelli, A.: Sensitivity analysis for importance assessment. Risk Anal. 22(3), 579–590 (2002)
26.
Schlichtkrull, M.S., Cao, N.D., Titov, I.: Interpreting graph neural networks for NLP with differentiable edge masking. In: ICLR (2021)
27.
Selvaraju, R., et al.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV (2017)
28.
Shapley, L.S.: A value for n-person games. Contrib. Theory Games 2(28), 307–317 (1953)
29.
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: ICML (2017)
30.
Strumbelj, E., Kononenko, I.: An efficient explanation of individual classifications using game theory. JMLR 11, 1–18 (2010)
31.
Ustun, B., Rudin, C.: Methods and models for interpretable linear classification. arXiv (2014)
32.
Vu, M.N., Thai, M.T.: PGM-explainer: probabilistic graphical model explanations for graph neural networks. In: NeurIPS (2020)
33.
Ying, Z., Bourgeois, D., You, J., Zitnik, M., Leskovec, J.: GNNExplainer: generating explanations for graph neural networks. In: NeurIPS (2019)
34.
Yuan, H., Tang, J., Hu, X., Ji, S.: XGNN: towards model-level explanations of graph neural networks. In: KDD (2020)
35.
36.
Zhang, M., Chen, Y.: Link prediction based on graph neural networks (2018)
37.
Zhou, J., et al.: Graph neural networks: a review of methods and applications. arXiv (2018)
Metadata
Title
GraphSVX: Shapley Value Explanations for Graph Neural Networks
Authors
Alexandre Duval
Fragkiskos D. Malliaros
Copyright Year
2021
Book
Machine Learning and Knowledge Discovery in Databases. Research Track

Print ISBN: 978-3-030-86519-1

Electronic ISBN: 978-3-030-86520-7

Copyright Year: 2021

DOI
https://doi.org/10.1007/978-3-030-86520-7_19

Premium Partner

    Image Credits