A multi-scale approach for graph link prediction
Deep models can be made scale-invariant when trained with multi-scale information.
Images can be easily made multi-scale, given their grid-like structures. Extending this to …
Images can be easily made multi-scale, given their grid-like structures. Extending this to …
Line graph neural networks for link prediction
We consider the graph link prediction task, which is a classic graph analytical problem with
many real-world applications. With the advances of deep learning, current link prediction …
many real-world applications. With the advances of deep learning, current link prediction …
Link prediction approach combined graph neural network with capsule network
Abstract Graph Neural Networks (GNNs, in short) are a powerful computational tool to jointly
learn graph structure and node/edge features. They achieved an unprecedented accuracy in …
learn graph structure and node/edge features. They achieved an unprecedented accuracy in …
Neural link prediction with walk pooling
L Pan, C Shi, I Dokmanić - arXiv preprint arXiv:2110.04375, 2021 - arxiv.org
Graph neural networks achieve high accuracy in link prediction by jointly leveraging graph
topology and node attributes. Topology, however, is represented indirectly; state-of-the-art …
topology and node attributes. Topology, however, is represented indirectly; state-of-the-art …
Bring your own view: Graph neural networks for link prediction with personalized subgraph selection
Graph neural networks (GNNs) have received remarkable success in link prediction
(GNNLP) tasks. Existing efforts first predefine the subgraph for the whole dataset and then …
(GNNLP) tasks. Existing efforts first predefine the subgraph for the whole dataset and then …
Multi-scale variational graph autoencoder for link prediction
Z Guo, F Wang, K Yao, J Liang, Z Wang - Proceedings of the Fifteenth …, 2022 - dl.acm.org
Link prediction has become a significant research problem in deep learning, and the graph-
based autoencoder model is one of the most important methods to solve it. The existing …
based autoencoder model is one of the most important methods to solve it. The existing …
Neo-gnns: Neighborhood overlap-aware graph neural networks for link prediction
Abstract Graph Neural Networks (GNNs) have been widely applied to various fields for
learning over graph-structured data. They have shown significant improvements over …
learning over graph-structured data. They have shown significant improvements over …
Evaluating graph neural networks for link prediction: Current pitfalls and new benchmarking
Link prediction attempts to predict whether an unseen edge exists based on only a portion of
the graph. A flurry of methods has been created in recent years that attempt to make use of …
the graph. A flurry of methods has been created in recent years that attempt to make use of …
An ensemble model for link prediction based on graph embedding
YL Chen, CH Hsiao, CC Wu - Decision Support Systems, 2022 - Elsevier
A network is a form of data representation and is widely used in many fields. For example, in
social networks, we regard nodes as individuals or groups, and the edges between nodes …
social networks, we regard nodes as individuals or groups, and the edges between nodes …
Link prediction on complex networks: an experimental survey
Complex networks have been used widely to model a large number of relationships. The
outbreak of COVID-19 has had a huge impact on various complex networks in the real …
outbreak of COVID-19 has had a huge impact on various complex networks in the real …