Fuzzy Neural Network for Representation Learning on Uncertain Graphs
- 25 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 32 (9) , 5259-5271
Abstract
Graph representation learning (GRL) focuses on abstracting critical information from raw graphs. Unfortunately, there always exist various kinds of uncertainties such as attribute noise and network topology corruption in raw graphs. Under the message passing mechanism, these uncertainties are likely to spread throughout the whole graph. Matters like these would induce deep graph models into producing uncertain representations and restrict representation expressiveness. Considering this, we propose a pioneering framework to defend graph uncertainties by improving the robustness and capability of graph neural networks (GNNs). In our framework, we consider that weights and biases are all fuzzy numbers, thus generating representations to assimilate graph uncertainties which are finally released by defuzzification. To describe the process of the framework, in this paper, a graph convolutional network (GCN) is employed to construct a robust graph model, called FuzzyGCN. To verify the effectiveness of FuzzyGCN, it is trained in both supervised and unsupervised ways. In the supervised setting, we find that FuzzyGCN has stronger power and is more immune to data uncertainties when compared with various classical and robust GNNs. In the unsupervised setting, FuzzyGCN surpasses many state-of-the-art models in node classification and community detection over several real-world datasets.Keywords
Funding Information
- National Natural Science Foundation of China (62076065)
- Natural Science Foundation of Fujian Province (2020J01495)
This publication has 31 references indexed in Scilit:
- RGCNU: Recurrent Graph Convolutional Network With Uncertainty Estimation for Remaining Useful Life PredictionIEEE/CAA Journal of Automatica Sinica, 2023
- Minority-Weighted Graph Neural Network for Imbalanced Node Classification in Social Networks of Internet of PeopleIEEE Internet of Things Journal, 2022
- A Progressive Quadric Graph Convolutional Network for 3D Human Mesh RecoveryIEEE Transactions on Circuits and Systems for Video Technology, 2022
- Sampling Methods for Efficient Training of Graph Convolutional Networks: A SurveyIEEE/CAA Journal of Automatica Sinica, 2021
- Semantic segmentation of breast ultrasound image with fuzzy deep learning network and breast anatomy constraintsNeurocomputing, 2021
- Graph deconvolutional networksInformation Sciences, 2020
- Calculator for fuzzy numbersComplex & Intelligent Systems, 2019
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- A hybrid fuzzy regression model and its application in hydrology engineeringApplied Soft Computing, 2014
- Perceptual Reasoning for Perceptual Computing: A Similarity-Based ApproachIEEE Transactions on Fuzzy Systems, 2009