IE Olatunji, A Hizber, O Sihlovec, M Khosla - arXiv preprint arXiv …, 2023 - arxiv.org
Graph neural networks (GNNs) have shown promising results on real-life datasets and applications, including healthcare, finance, and education. However, recent studies have …
Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb …
Graph structured data have enabled several successful applications such as recommendation systems and traffic prediction, given the rich node features and edges …
X Li, L Chen, D Wu - International Conference on Security and Privacy in …, 2022 - Springer
As social networks become indispensable for people's daily lives, inference attacks pose significant threat to users' privacy where attackers can infiltrate users' information and infer …
Graph Neural Networks (GNNs) are a popular technique for modelling graph-structured data and computing node-level representations via aggregation of information from the …
IC Hsieh, CT Li - IEEE Transactions on Knowledge and Data …, 2021 - ieeexplore.ieee.org
Recent advances in protecting node privacy on graph data and attacking graph neural networks (GNNs) gain much attention. The eye does not bring these two essential tasks …
Graph Neural Networks (GNNs) have demonstrated superior performance in learning node representations for various graph inference tasks. However, learning over graph data can …
While graph neural networks (GNNs) dominate the state-of-the-art for exploring graphs in real-world applications, they have been shown to be vulnerable to a growing number of …
W Lin, H Lan, J Cao - IEEE Transactions on Dependable and …, 2024 - ieeexplore.ieee.org
This paper investigates the problem of learning privacy-preserving graph representations with graph neural networks (GNNs). Different from existing works based on adversarial …