research-article

RelEx: A Model-Agnostic Relational Model Explainer

Authors:

Arti RameshAuthors Info & Claims

AIES '21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society

Pages 1042 - 1049

https://doi.org/10.1145/3461702.3462562

Published: 30 July 2021 Publication History

Abstract

In recent years, considerable progress has been made on improving the interpretability of machine learning models. This is essential, as complex deep learning models with millions of parameters produce state of the art performance, but it can be nearly impossible to explain their predictions. While various explainability techniques have achieved impressive results, nearly all of them assume each data instance to be independent and identically distributed (iid). This excludes relational models, such as Statistical Relational Learning (SRL), and the recently popular Graph Neural Networks (GNNs), resulting in few options to explain them. While there does exist work on explaining GNNs, GNN-Explainer, they assume access to the gradients of the model to learn explanations, which is restrictive in terms of its applicability across non-differentiable relational models and practicality. In this work, we develop RelEx, amodel-agnostic relational explainer to explain black-box relational models with only access to the outputs of the black-box. RelEx is able to explain any relational model, including SRL models and GNNs. We compare RelEx to the state-of-the-art relational explainer, GNN-Explainer, and relational extensions of iid explanation models and show that RelEx achieves comparable or better performance, while remaining model-agnostic.

References

[1]

Stephen H Bach, Matthias Broecheler, Bert Huang, and Lise Getoor. 2017. Hinge-loss markov random fields and probabilistic soft logic. Journal of Machine Learning Research (JMLR) (2017), 3846--3912.

[2]

Asim Kumar Debnath, Rosa L. Lopez de Compadre, Gargi Debnath, Alan J. Shusterman, and Corwin Hansch. 1991. Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity. Journal of Medicinal Chemistry (1991), 786--797.

[3]

Nima Dehmamy, Albert-László Barabási, and Rose Yu. 2019. Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology. In Proceedings of the conference on neural information processing systems (NeurIPS).

[4]

Matthias Fey and Jan E. Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. In Proceedings of the ICLR Workshop on Representation Learning on Graphs and Manifolds.

[5]

Ben Taskar Lise Getoor (Ed.). 2007. Introduction to Statistical Relational Learning (Adaptive Computation and Machine Learning).

[6]

Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. Proceedings of the international conference on learning representations (ICLR) (2015).

[7]

Jun He, Yue Zhang, Yuan Zhou, and Lei Zhang. 2016. Adaptive stochastic gradient descent on the Grassmannian for robust low-rank subspace recovery. IET Signal Processing (2016), 1000--1008.

[8]

Qiang Huang, Makoto Yamada, Yuan Tian, Dinesh Singh, Dawei Yin, and Yi Chang. 2020. GraphLIME: Local interpretable model explanations for graph neural networks. arXiv:2001.06216 (2020).

[9]

Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax. arXiv:1611.01144 (2016).

[10]

Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In Proceedings of the international conference on learning representations (ICLR).

[11]

Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In Proceedings of the international conference on machine learning (ICML).

[12]

Jianxin Ma, Peng Cui, Kun Kuang, Xin Wang, and Wenwu Zhu. 2019. Disentangled graph convolutional networks. In Proceedings of the international conference on machine learning (ICML).

[13]

Ramaravind K Mothilal, Amit Sharma, and Chenhao Tan. 2020. Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the conference on fairness, accountability, and transparency (FAT).

Digital Library

[14]

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. Why should i trust you?: Explaining the predictions of any classifier. In Proceedings of the SIGKDD conference on Knowledge Discovery and Data Mining (KDD).

Digital Library

[15]

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Anchors: High-precision model-agnostic explanations. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI).

[16]

Andrew Slavin Ross, Michael C Hughes, and Finale Doshi-Velez. 2017. Right for the right reasons: Training differentiable models by constraining their explanations. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (2017).

[17]

Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. IEEE Transactions on Neural Networks (2008), 61--80.

Digital Library

[18]

Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T Schütt, Klaus-Robert Müller, and Grégoire Montavon. 2020. XAI for Graphs: Explaining Graph Neural Network Predictions by Identifying Relevant Walks. arXiv:2006.03589 (2020).

[19]

Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda Viégas, and Martin Wattenberg. 2017. Smoothgrad: removing noise by adding noise. arXiv:1706.03825 (2017).

[20]

Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In Proceedings of the international conference on machine learning (ICML).

[21]

Petar Velivc ković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. Proceedings of the international conference on learning representations (ICLR) (2018).

[22]

Minh Vu and My T Thai. 2020. PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks. Proceedings of the conference on Advances in Neural Information Processing Systems (NeurIPS) (2020).

[23]

Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying Graph Convolutional Networks. In Proceedings of the international conference on machine learning (ICML).

[24]

Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In Proceedings of the international conference on learning representations (ICLR).

[25]

Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Suggala, David I Inouye, and Pradeep K Ravikumar. 2019. On the (In) fidelity and Sensitivity of Explanations. In Proceedings of the conference on neural information processing systems (NeurIPS).

[26]

Chih-Kuan Yeh, Joon Kim, Ian En-Hsu Yen, and Pradeep K Ravikumar. 2018. Representer point selection for explaining deep neural networks. In Proceedings of the conference on neural information processing systems (NeurIPS).

[27]

Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019. GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks. In Proceedings of the conference on neural information processing systems (NeurIPS).

[28]

Yue Zhang and Arti Ramesh. 2019. Learning interpretable relational structures of hinge-loss Markov random fields. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI).

Cited By

Karamanou ABrimos PKalampokis ETarabanis K(2024)Explainable Graph Neural Networks: An Application to Open Statistics Knowledge Graphs for Estimating House PricesTechnologies10.3390/technologies1208012812:8(128)Online publication date: 6-Aug-2024
https://doi.org/10.3390/technologies12080128
Shi CZhu MYu YWang XDu J(2024)Unifying Graph Neural Networks with a Generalized Optimization FrameworkACM Transactions on Information Systems10.1145/366085242:6(1-32)Online publication date: 19-Aug-2024
https://dl.acm.org/doi/10.1145/3660852
Jeon MPark JOh H(2024)PL4XGL: A Programming Language Approach to Explainable Graph LearningProceedings of the ACM on Programming Languages10.1145/36564648:PLDI(2148-2173)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3656464
Show More Cited By

Index Terms

RelEx: A Model-Agnostic Relational Model Explainer
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Logical and relational learning
        Statistical relational learning

Recommendations

Modeling MongoDB with Relational Model
EIDWT '13: Proceedings of the 2013 Fourth International Conference on Emerging Intelligent Data and Web Technologies

Relational databases have been prevailing for the last two decades, with features of clear semantics and ease of use with SQL supported by the underlying theory, relational algebra. Relational databases provide good support for structural data ...
Nested bitemporal relational data model
ILIME: Local and Global Interpretable Model-Agnostic Explainer of Black-Box Decision
Advances in Databases and Information Systems
Abstract
Despite outperforming humans in different supervised learning tasks, complex machine learning models are criticised for their opacity which make them hard to trust especially when used in critical domains (e.g., healthcare, self-driving car). ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

AIES '21: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society

July 2021

1077 pages

ISBN:9781450384735

DOI:10.1145/3461702

Program Chairs:
Marion Fourcade
University of California Berkeley, USA
,
Benjamin Kuipers
University of Michigan, USA
,
Seth Lazar
Australian National University, Australia
,
Deirdre Mulligan
University of California Berkeley, USA

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 30 July 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

AIES '21

Sponsor:

SIGAI

AIES '21: AAAI/ACM Conference on AI, Ethics, and Society

May 19 - 21, 2021

Virtual Event, USA

Acceptance Rates

Overall Acceptance Rate 61 of 162 submissions, 38%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

34
Total Citations
View Citations
420
Total Downloads

Downloads (Last 12 months)113
Downloads (Last 6 weeks)11

Reflects downloads up to 22 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Karamanou ABrimos PKalampokis ETarabanis K(2024)Explainable Graph Neural Networks: An Application to Open Statistics Knowledge Graphs for Estimating House PricesTechnologies10.3390/technologies1208012812:8(128)Online publication date: 6-Aug-2024
https://doi.org/10.3390/technologies12080128
Shi CZhu MYu YWang XDu J(2024)Unifying Graph Neural Networks with a Generalized Optimization FrameworkACM Transactions on Information Systems10.1145/366085242:6(1-32)Online publication date: 19-Aug-2024
https://dl.acm.org/doi/10.1145/3660852
Jeon MPark JOh H(2024)PL4XGL: A Programming Language Approach to Explainable Graph LearningProceedings of the ACM on Programming Languages10.1145/36564648:PLDI(2148-2173)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3656464
Cheng BZhao SWang KWang MBai GFeng RGuo YMa LWang H(2024)Beyond Fidelity: Explaining Vulnerability Localization of Learning-Based DetectorsACM Transactions on Software Engineering and Methodology10.1145/364154333:5(1-33)Online publication date: 4-Jun-2024
https://dl.acm.org/doi/10.1145/3641543
Akkas SAzad AChua TNgo CKa-Wei Lee RKumar RLauw H(2024)GNNShap: Scalable and Accurate GNN Explanation using Shapley ValuesProceedings of the ACM Web Conference 202410.1145/3589334.3645599(827-838)Online publication date: 13-May-2024
https://dl.acm.org/doi/10.1145/3589334.3645599
Chhablani CJain SChannesh AKash IMedya SChua TNgo CKa-Wei Lee RKumar RLauw H(2024)Game-theoretic Counterfactual Explanation for Graph Neural NetworksProceedings of the ACM Web Conference 202410.1145/3589334.3645419(503-514)Online publication date: 13-May-2024
https://dl.acm.org/doi/10.1145/3589334.3645419
Zhang HWu BYuan XPan STong HPei J(2024)Trustworthy Graph Neural Networks: Aspects, Methods, and TrendsProceedings of the IEEE10.1109/JPROC.2024.3369017112:2(97-139)Online publication date: Feb-2024
https://doi.org/10.1109/JPROC.2024.3369017
Saqib MFung BCharland PWalenstein A(2024)GAGE: Genetic Algorithm-Based Graph Explainer for Malware Analysis2024 IEEE 40th International Conference on Data Engineering (ICDE)10.1109/ICDE60146.2024.00179(2258-2270)Online publication date: 13-May-2024
https://doi.org/10.1109/ICDE60146.2024.00179
Schramm SWehner CSchmid U(2024)Comprehensible Artificial Intelligence on Knowledge GraphsWeb Semantics: Science, Services and Agents on the World Wide Web10.1016/j.websem.2023.10080679:COnline publication date: 4-Mar-2024
https://dl.acm.org/doi/10.1016/j.websem.2023.100806
Zhang YCheung WLiu QWang GYang LLiu L(2024)Towards explaining graph neural networks via preserving prediction ranking and structural dependencyInformation Processing and Management: an International Journal10.1016/j.ipm.2023.10357161:2Online publication date: 12-Apr-2024
https://dl.acm.org/doi/10.1016/j.ipm.2023.103571
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents