Fuzzy Graph Neural Networks: A Comprehensive Review of Uncertainty-Aware Graph Learning

Ngoc Dan Tran; Thi Nhung Tong; Thi Kim Phung Nguyen; Thi Hong Tu Nguyen

doi:10.4108/eetcasa.9483

Authors

Ngoc Dan Tran Thuyloi University
Thi Nhung Tong Thuyloi University
Thi Kim Phung Nguyen Thuyloi University
Thi Hong Tu Nguyen Thuyloi University

DOI:

https://doi.org/10.4108/eetcasa.9483

Keywords:

Fuzzy Graph Neural Networks, Graph Neural Networks, Graph Representation Learning, Explainable

Abstract

Graph Neural Networks (GNNs) have become powerful tools for learning from graph-structured data. However, traditional GNNs often fail to address uncertainty inherent in many real-world applications. Fuzzy Graph Neural Networks (FGNNs) integrate fuzzy logic into GNNs to provide a robust mechanism for managing uncertainty, imprecision, and vagueness. This paper presents a comprehensive review of FGNNs, examining their theoretical underpinnings, methodologies, applications, challenges, and potential research directions.

References

[1] William L Hamilton, Rex Ying, and Jure Leskovec. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems (NeurIPS), volume 30, 2017.

[2] Jyh-Shing Roger Jang. Anfis: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3):665–685, 1993.Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.

[4] Y. Li, X. Zhang, J. Wang, and Q. Liu. Large-scale data classification based on the integrated fusion of fuzzy learning and graph neural networks. Information Fusion, 89:1–12, 2023.

[5] Xia Liu, Yali Wang, and Yujie Zhang. Fuzzy graph neural networks in cyber-physical systems. IEEE Internet of Things Journal, 8(3):1 12, 2021.

[6] Xia Liu, Yali Wang, and Yujie Zhang. Fuzzy graph neural networks for social network analysis. Social Network Analysis and Mining, 13(1):1–15, 2023.

[7] Ebrahim H Mamdani and Sedrak Assilian. An experiment in linguistic synthesis with a fuzzy logic controller. International Journal of Man-Machine Studies, 7(1):1–13, 1975.

[8] Michio Sugeno. Industrial Applications of Fuzzy Control. Elsevier Science Inc., New York, 1985.

[9] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. In International Conference on Learning Representations (ICLR), 2018.

[10] Hao Wang, Min Li, and Yu Chen. Fuzzy graph neural networks in healthcare. Journal of Biomedical Informatics, 94:1–12, 2019.

[11] Hao Wang, Min Li, and Yu Chen. Fuzzy graph neural networks in bioinformatics: A survey. Briefings in Bioinformatics, 24(2):1–12, 2023.

[12] Yuxuan Wu, Min Li, Yujie Zhang, Yuxuan Liu, and Yali Wang. Hfgnn-proto: Hesitant fuzzy graph neural network-based few-shot text classification. Electronics, 11(15):2423, 2022.

[13] Jinming Xing, Ruilin Xing, Chang Xue, and Dongwen Luo. Enhancing link prediction with fuzzy graph attention networks and dynamic negative sampling. arXiv preprint arXiv:2411.07482, 2024.

[14] Lotfi A Zadeh. Fuzzy sets. Information and Control, 8(3):338–353, 1965.

[15] Lei Zhang, Wei Liu, and Yu Chen. Fuzzy graph neural networks for recommendation systems. IEEE Transactions on Knowledge and Data Engineering, 34(5):1–10, 2022.

[16] Wei Zhang, Xia Liu, Ming Chen, and Lin Zhao. Accurate learning of graph representation with the consideration of fuzzy overlapping community. Neurocomputing, 512:1–10, 2024.

[17] Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. Graph neural networks: A review of methods and applications. arXiv preprint arXiv:1812.08434, 2018.