Finding the proper depth $ d $ of a graph convolutional network (GCN) that provides strong representation ability has drawn significant attention, yet nonetheless largely remains an …
Z Zeng, B Du, S Zhang, Y Xia, Z Liu… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Finding node correspondence across networks, namely multi-network alignment, is an essential prerequisite for joint learning on multiple networks. Despite great success in …
Y Yan, Y Hu, Q Zhou, L Liu, Z Zeng, Y Chen… - Proceedings of the …, 2024 - dl.acm.org
Network embedding plays an important role in a variety of social network applications. Existing network embedding methods, explicitly or implicitly, can be categorized into …
A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to …
Graph pre-training strategies have been attracting a surge of attention in the graph mining community, due to their flexibility in parameterizing graph neural networks (GNNs) without …
Graphs are powerful representations for relations among objects, which have attracted plenty of attention in both academia and industry. A fundamental challenge for graph …
D Fu, J He - 2022 IEEE International Conference on Big Data …, 2022 - ieeexplore.ieee.org
In the big data era, the relationship between entries becomes more and more complex. Many graph (or network) algorithms have already paid attention to dynamic networks, which …
J Wu, W Fan, S Liu, Q Liu, Q Li, K Tang - arXiv preprint arXiv:2309.12723, 2023 - arxiv.org
Graph-based collaborative filtering has emerged as a powerful paradigm for delivering personalized recommendations. Despite their demonstrated effectiveness, these methods …
Contrastive learning is an effective unsupervised method in graph representation learning. The key component of contrastive learning lies in the construction of positive and negative …