Proceedings of the 2023 2nd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2023)

<Previous Article In Volume
Next Article In Volume>

Explanations for Graph Neural Networks via Layer Analysis

Authors
Qinfeng Li1, Xinrui Kang1, Wenyuan Li1, Dong Liang2, *
1School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China
2Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, China
*Corresponding author. Email: liangdong@bupt.edu.cn
Corresponding Author
Dong Liang
Available Online 28 August 2023.
DOI
10.2991/978-94-6463-222-4_43How to use a DOI?
Keywords
Graph Neural Networks; Explanations; Model-level; Generation
Abstract

Like many deep learning models, graph neural networks (GNNs) are regarded as black boxes and lack interpretability. Therefore, it is difficult for GNNs to be fully trusted by humans to be applied to various life scenarios. Based on this problem, we propose a new interpretability method called LAExplainer, which is used to explain GNNs hierarchically at the model level. In particular, LAExplainer not only focuses on the overall interpretation of the model, but also analyzes the interpretation problems between layers. Our approach interprets the middle-level process of the model through layer-by-layer analysis, and uses it as a basis to guide the construction of sub-graphs to reduce the size of the sub-graph set, which effectively explain the overall model. In addition, the approach will analyze the importance of model features and produce an adjustable principal component selection mechanism. In terms of evaluation indicators, we propose to set hyperparameters so that the two results of Fidelity and Sparsity can be changed simultaneously by adjusting the hyperparameters during the interpretation of GNNs. Experimental results show that our proposed method is effective in synthetic data sets and real data sets, and the results of the visualized sub-graphs are more in line with human understanding.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2023 2nd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2023)
Series
Atlantis Highlights in Intelligent Systems
Publication Date
28 August 2023
ISBN
10.2991/978-94-6463-222-4_43
ISSN
2589-4919
DOI
10.2991/978-94-6463-222-4_43How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Qinfeng Li
AU  - Xinrui Kang
AU  - Wenyuan Li
AU  - Dong Liang
PY  - 2023
DA  - 2023/08/28
TI  - Explanations for Graph Neural Networks via Layer Analysis
BT  - Proceedings of the 2023 2nd International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2023)
PB  - Atlantis Press
SP  - 397
EP  - 410
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-222-4_43
DO  - 10.2991/978-94-6463-222-4_43
ID  - Li2023
ER  -