ACGAN-GNNExplainer : Auxiliary conditional generative explainer for graph neural networks

Conference paper


Li, Yiqiao, Zhou, Jianlong, Dong, Yifei, Shafiabady, Niusha and Chen, Fang. (2023). ACGAN-GNNExplainer : Auxiliary conditional generative explainer for graph neural networks. 32nd ACM International Conference on Information and Knowledge Management (CIKM ’23). Birmingham, United Kingdom 21 - 25 Oct 2023 Association for Computing Machinery. pp. 1259-1267 https://doi.org/10.1145/3583780.3614772
AuthorsLi, Yiqiao, Zhou, Jianlong, Dong, Yifei, Shafiabady, Niusha and Chen, Fang
TypeConference paper
Abstract

Graph neural networks (GNNs) have proven their efficacy in a variety of real-world applications, but their underlying mechanisms remain a mystery. To address this challenge and enable reliable decision-making, many GNN explainers have been proposed in recent years. However, these methods often encounter limitations, including their dependence on specific instances, lack of generalizability to unseen graphs, producing potentially invalid explanations, and yielding inadequate fidelity. To overcome these limitations, we, in this paper, introduce the Auxiliary Classifier Generative Adversarial Network (ACGAN) into the field of GNN explanation and propose a new GNN explainer dubbed ACGAN-GNNExplainer. Our approach leverages a generator to produce explanations for the original input graphs while incorporating a discriminator to oversee the generation process, ensuring explanation fidelity and improving accuracy. Experimental evaluations conducted on both synthetic and real-world graph datasets demonstrate the superiority of our proposed method compared to other existing GNN explainers.

Keywordsgraph neural networks; explanations; graph neural network explainer; conditional generative adversarial network
Year2023
PublisherAssociation for Computing Machinery
Digital Object Identifier (DOI)https://doi.org/10.1145/3583780.3614772
Publisher's version
License
All rights reserved
File Access Level
Controlled
Book titleCIKM ’23 : Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
Page range1259-1267
ISBN9798400701245
Web address (URL) of conference proceedingshttps://doi.org/10.1145/3583780
Output statusPublished
Publication dates
Online21 Oct 2023
Publication process dates
Deposited28 May 2025
Additional information

© 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

Permalink -

https://acuresearchbank.acu.edu.au/item/91x93/acgan-gnnexplainer-auxiliary-conditional-generative-explainer-for-graph-neural-networks

Restricted files

Publisher's version

  • 4
    total views
  • 0
    total downloads
  • 0
    views this month
  • 0
    downloads this month
These values are for the period from 19th October 2020, when this repository was created.

Export as

Related outputs

Resource constraint crop damage classification using depth channel shuffling
Islam, Md Tanvir, Swapnil, Safkat Shahrier, Billal, Md. Masum, Karim, Asif, Shafiabady, Niusha and Hassan, Md. Mehedi. (2025). Resource constraint crop damage classification using depth channel shuffling. Engineering Applications of Artificial Intelligence. 144, p. Article 110117. https://doi.org/10.1016/j.engappai.2025.110117
Loss factor analysis in real-time structural health monitoring using a convolutional neural network
Nguyen, Thanh Q., Vu, Tu B., Shafiabady, Niusha, Nguyen, Thuy T. and Nguyen, Phuoc T.. (2025). Loss factor analysis in real-time structural health monitoring using a convolutional neural network. Archive of Applied Mechanics. 95(1), p. Article 15. https://doi.org/10.1007/s00419-024-02712-4
Application of CNN and MLP models for structural health monitoring : A case study on Saigon Bridge
Nguyen, Thanh Q., Vu, Tu B., Shafiabady, Niusha, Nguyen, Thuy T. and Nguyen, Phuoc T.. (2025). Application of CNN and MLP models for structural health monitoring : A case study on Saigon Bridge. Journal of Low Frequency Noise Vibration and Active Control. pp. 1-30. https://doi.org/10.1177/14613484251332711
Predicting postgraduate student engagement using artificial intelligence (AI)
Shafiabady, Niusha, Koo, Tebbin (Fung), Din, Fareed Ud, Sattarshetty, Kabir, Yen, Margaret, Alazab, Mamoun and Alsharaydeh, Ethar. (2025). Predicting postgraduate student engagement using artificial intelligence (AI). IEEE Transactions on Artificial Intelligence. pp. 1-12. https://doi.org/10.1109/TAI.2025.3548016
Applications of Explainable Artificial Intelligence (XAI) and interpretable Artificial Intelligence (AI) in smart buildings and energy savings in buildings : A systematic review
Haghighat, Mohammadreza, MohammadiSavadkoohi, Ehsan and Shafiabady, Niusha. (2025). Applications of Explainable Artificial Intelligence (XAI) and interpretable Artificial Intelligence (AI) in smart buildings and energy savings in buildings : A systematic review. Journal of Building Engineering. 107, p. Article 112542. https://doi.org/10.1016/j.jobe.2025.112542
Multi-dimensional perceptual recognition of tourist destination using deep learning model and geographic information system
Zhang, Shengtian, Li, Yong, Song, Xiaoxia, Yang, Chenghao, Shafiabady, Niusha and Wu, Robert M. X.. (2025). Multi-dimensional perceptual recognition of tourist destination using deep learning model and geographic information system. PLoS ONE. 20, p. Article e0318846. https://doi.org/10.1371/journal.pone.0318846
ECgMLP : A novel gated MLP model for enhanced endometrial cancer diagnosis
Sheakh, Md. Alif, Azam, Sami, Tahosin, Mst. Sazia, Karim, Asif, Montaha, Sidratul, Fahim, Kayes Uddin, Shafiabady, Niusha, Jonkman, Mirjam and De Boer, Friso. (2025). ECgMLP : A novel gated MLP model for enhanced endometrial cancer diagnosis. Computer Methods and Programs in Biomedicine Update. 7, p. Article 100181. https://doi.org/10.1016/j.cmpbup.2025.100181
Efficient energy utilization in smart grids an artificial intelligence perspective
Qadir, Zakria, Khan, Yasir Ali, Rana, Muhammad Tausif Afzal, Din, Fareed Ud and Shafiabady, Niusha. (2025). Efficient energy utilization in smart grids an artificial intelligence perspective. In In Bhatia, Tarandeep Kaur, El Hajjami, Salma, Kaushik, Keshav, Diallo, Gayo, Ouaissa, Mariya and Khan, Inam Ullah (Ed.). Ethical artificial intelligence in power electronics pp. 133-147 CRC Press. https://doi.org/10.1201/9781032648323-9
AI is everywhere – including countless applications you’ve likely never heard of
Shafiabady, Niusha. (2024). AI is everywhere – including countless applications you’ve likely never heard of The Conversation Media Group.
Reliable and faithful generative explainers for graph neural networks
Li, Yiqiao, Zhou, Jianlong, Zheng, Boyuan, Shafiabady, Niusha and Chen, Fang. (2024). Reliable and faithful generative explainers for graph neural networks. Machine Learning and Knowledge Extraction. 6(4), pp. 2913-2929. https://doi.org/10.3390/make6040139
Automated diagnosis of respiratory diseases from lung ultrasound videos ensuring XAI : An innovative hybrid model approach
Abian, Arefin Ittesafun, Khan Raiaan, Mohaimenul Azam, Karim, Asif, Azam, Sami, Fahad, Nur Mohammad, Shafiabady, Niusha, Yeo, Kheng Cher and De Boer, Friso. (2024). Automated diagnosis of respiratory diseases from lung ultrasound videos ensuring XAI : An innovative hybrid model approach. Frontiers in Computer Science. 6, p. Article 1438126. https://doi.org/10.3389/fcomp.2024.1438126
eXplainable Artificial Intelligence (XAI) for improving organisational regility
Shafiabady, Niusha, Hadjinicolaou, Nick, Hettikankanamage, Nadeesha, MohammadiSavadkoohi, Ehsan, Wu, Robert M. X. and Vakilian, James. (2024). eXplainable Artificial Intelligence (XAI) for improving organisational regility. PLoS ONE. 19(4), p. Article e0301429. https://doi.org/10.1371/journal.pone.0301429
Real-time structural health monitoring of bridges using convolutional neural network-based loss factor analysis for enhanced energy dissipation detection
Nguyen, Thanh Q., Vu, Tu B., Shafiabady, Niusha, Nguyen, Thuy T. and Nguyen, Phuoc T.. (2024). Real-time structural health monitoring of bridges using convolutional neural network-based loss factor analysis for enhanced energy dissipation detection. Structures. 70, p. Article 107733. https://doi.org/10.1016/j.istruc.2024.107733
Comparative study of ten machine learning algorithms for short-term forecasting in gas warning systems
Wu, Robert M.X., Shafiabady, Niusha, Zhang, Huan, Lu, Haiyan, Gide, Ergun, Liu, Jinrong and Charbonnier, Clement Franck Benoit. (2024). Comparative study of ten machine learning algorithms for short-term forecasting in gas warning systems. Scientific Reports. 14(1), pp. 1-18. https://doi.org/10.1038/s41598-024-67283-4
Whose job will AI replace? Here’s why a clerk in Ethiopia has more to fear than one in California
Shafiabady, Niusha. (2023). Whose job will AI replace? Here’s why a clerk in Ethiopia has more to fear than one in California The Conversation Media Group.
Using Artificial Intelligence (AI) to predict organizational agility
Shafiabady, Niusha, Hadjinicolaou, Nick, Din, Fareed Ud, Bhandari, Binayak, Wu, Robert M. X. and Vakilian, James. (2023). Using Artificial Intelligence (AI) to predict organizational agility. PLoS ONE. 18(5), p. Article e0283066. https://doi.org/10.1371/journal.pone.0283066
Using multi-focus group method as an effective tool for eliciting business system requirements : Verified by a case study
Wu, Robert M. X., Wang, Yongwen, Shafiabady, Niusha, Zhang, Huan, Yan, Wanjun, Gou, Jinwen, Shi, Yong, Liu, Bao, Gide, Ergun, Kang, Changlong, Zhang, Zhongwu, Shen, Bo, Li, Xiaoquan, Fan, Jianfeng, He, Xiangqian, Soar, Jeffrey, Zhao, Haijun, Sun, Lei, Huo, Wenying and Wang, Ya. (2023). Using multi-focus group method as an effective tool for eliciting business system requirements : Verified by a case study. PLoS ONE. 18(3), p. Article e0281603. https://doi.org/10.1371/journal.pone.0281603
Identifying presence of cybersickness symptoms using AI-based predictive learning algorithms
Zaidi, Syed Fawad M., Shafiabady, Niusha and Beilby, Justin. (2023). Identifying presence of cybersickness symptoms using AI-based predictive learning algorithms. Virtual Reality. 27(4), pp. 3613-3620. https://doi.org/10.1007/s10055-023-00813-z
V-CarE—A conceptual conceptual design model for providing COVID-19 pandemic awareness : Proposal for a virtual reality design approach to facilitate people with persistent postural-perceptual dizziness
Zaidi, Syed Fawad M., Shafiabady, Niusha, Afifi, Shereen and Beilby, Justin. (2023). V-CarE—A conceptual conceptual design model for providing COVID-19 pandemic awareness : Proposal for a virtual reality design approach to facilitate people with persistent postural-perceptual dizziness. JMIR Research Protocols. 12, p. Article e38369. https://doi.org/10.2196/38369
An FSV analysis approach to verify the robustness of the triple-correlation analysis theoretical framework
Wu, Robert M. X., Zhang, Zhongwu, Zhang, Huan, Wang, Yongwen, Shafiabady, Niusha, Yan, Wanjun, Gou, Jinwen, Gide, Ergun and Zhang, Siqing. (2023). An FSV analysis approach to verify the robustness of the triple-correlation analysis theoretical framework. Scientific Reports. 13(1), p. Article 9621. https://doi.org/10.1038/s41598-023-35900-3
Implementation of transformer-based deep learning architecture for the development of surface roughness classifier using sound and cutting force signals
Bhandari, Binayak, Park, Gijun and Shafiabady, Niusha. (2023). Implementation of transformer-based deep learning architecture for the development of surface roughness classifier using sound and cutting force signals. Neural Computing and Applications. 35(18), pp. 13275-13292. https://doi.org/10.1007/s00521-023-08425-z
Persistent postural-perceptual dizziness interventions—an embodied insight on the use virtual reality for technologists
Zaidi, Syed Fawad M., Shafiabady, Niusha and Beilby, Justin. (2022). Persistent postural-perceptual dizziness interventions—an embodied insight on the use virtual reality for technologists. Electronics. 11(1), p. Article 142. https://doi.org/10.3390/electronics11010142
Evolving Hybrid partial genetic algorithm classification model for cost-effective frailty screening : Investigative study
Oates, John, Shafiabady, Niusha, Ambagtsheer, Rachel, Beilby, Justin, Seiboth, Chris and Dent, Elsa. (2022). Evolving Hybrid partial genetic algorithm classification model for cost-effective frailty screening : Investigative study. JMIR Aging. 5(4), p. Article e38464. https://doi.org/10.2196/38464
The application of artificial intelligence (AI) techniques to identify frailty within a residential aged care administrative data set
Ambagtsheer, R. C., Shafiabady, N., Dent, E., Seiboth, C. and Beilby, J.. (2020). The application of artificial intelligence (AI) techniques to identify frailty within a residential aged care administrative data set. International Journal of Medical Informatics. 136, p. Article 104094. https://doi.org/10.1016/j.ijmedinf.2020.104094
ST (Shafiabady-Teshnehlab) optimization algorithm
Shafiabady, Niusha. (2018). ST (Shafiabady-Teshnehlab) optimization algorithm. In In Tan, Ying (Ed.). Swarm intelligence : Volume 2 : Innovation, new algorithms and methods pp. 83-110 The Institution of Engineering and Technology. https://doi.org/10.1049/pbce119g_ch4
Acute effects of methadone on EEG power spectrum and event-related potentials among heroin dependents
Motlagh, Farid, Ibrahim, Fatimah, Rashid, Rusdi, Shafiabady, Niusha, Seghatoleslam, Tahereh and Habil, Hussain. (2018). Acute effects of methadone on EEG power spectrum and event-related potentials among heroin dependents. Psychopharmacology. 235(11), pp. 3273-3288. https://doi.org/10.1007/s00213-018-5035-0