Multi-level graph convolutional networks for cross-platform anchor link prediction

H Chen, H Yin, X Sun, T Chen, B Gabrys… - Proceedings of the 26th …, 2020 - dl.acm.org
Cross-platform account matching plays a significant role in social network analytics, and is
beneficial for a wide range of applications. However, existing methods either heavily rely on …

Adapting membership inference attacks to GNN for graph classification: Approaches and implications

B Wu, X Yang, S Pan, X Yuan - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
In light of the wide application of Graph Neural Networks (GNNs), Membership Inference
Attack (MIA) against GNNs raises severe privacy concerns, where training data can be …

Adaptive network alignment with unsupervised and multi-order convolutional networks

HT Trung, T Van Vinh, NT Tam, H Yin… - 2020 IEEE 36th …, 2020 - ieeexplore.ieee.org
Network alignment is the problem of pairing nodes between two graphs such that the paired
nodes are structurally and semantically similar. A well-known application of network …

Space4hgnn: a novel, modularized and reproducible platform to evaluate heterogeneous graph neural network

T Zhao, C Yang, Y Li, Q Gan, Z Wang, F Liang… - Proceedings of the 45th …, 2022 - dl.acm.org
Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various
tasks, but we cannot accurately know the importance of different design dimensions of …

Entity alignment for knowledge graphs with multi-order convolutional networks

NT Tam, HT Trung, H Yin, T Van Vinh… - … on Knowledge and …, 2020 - ieeexplore.ieee.org
Knowledge graphs (KGs) have become popular structures for unifying real-world entities by
modelling the relationships between them and their attributes. To support multilingual …

An efficient and effective framework for session-based social recommendation

T Chen, RCW Wong - Proceedings of the 14th ACM international …, 2021 - dl.acm.org
In many applications of session-based recommendation, social networks are usually
available. Since users' interests are influenced by their friends, recommender systems can …

Data analytics of social media 3.0: Privacy protection perspectives for integrating social media and Internet of Things (SM-IoT) systems

S Salim, B Turnbull, N Moustafa - Ad Hoc Networks, 2022 - Elsevier
With the rapid evolution of web technologies, Web 3.0 aims to expand on current and
emerging social media platforms such as Facebook, Twitter, and TikTok, and integrate …

Adversarial-enhanced hybrid graph network for user identity linkage

X Chen, X Song, G Peng, S Feng, L Nie - Proceedings of the 44th …, 2021 - dl.acm.org
In this work, we investigate the user identity linkage task across different social media
platforms based on heterogeneous multi-modal posts and social connections. This task is …

Atlrec: An attentional adversarial transfer learning network for cross-domain recommendation

Y Li, JJ Xu, PP Zhao, JH Fang, W Chen… - Journal of Computer …, 2020 - Springer
Entity linking is a new technique in recommender systems to link users' interaction behaviors
in different domains, for the purpose of improving the performance of the recommendation …

Multi-level hyperedge distillation for social linking prediction on sparsely observed networks

X Sun, H Yin, B Liu, H Chen, Q Meng, W Han… - Proceedings of the Web …, 2021 - dl.acm.org
Social linking prediction is one of the most fundamental problems in online social networks
and has attracted researchers' persistent attention. Most of the existing works predict …