This paper is the first to use contrastive learning to improve the robustness of graph representation learning for signed bipartite graphs, which are commonly found in social …
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 …
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 …
There have been tremendous efforts over the past decades dedicated to the generation of realistic graphs in a variety of domains, ranging from social networks to computer networks …
In the era of big data and Artificial Intelligence, an emerging paradigm is to utilize contrastive self-supervised learning to model large-scale heterogeneous data. Many existing foundation …
H Xu, Y Yan, D Wang, Z Xu, Z Zeng… - Forty-first International … - openreview.net
Graph neural networks (GNNs) have exhibited superb power in many graph related tasks. Existing GNNs can be categorized into spatial GNNs and spectral GNNs. The spatial GNNs …
Z Zeng, R Qiu, Z Xu, Z Liu, Y Yan, T Wei, L Ying… - Forty-first International … - openreview.net
Mixup, which generates synthetic training samples on the data manifold, has been shown to be highly effective in augmenting Euclidean data. However, finding a proper data manifold …