scholar.google.com › citations
Line graph contrastive learning for node classification
LineGCL utilizes the characteristics of line graphs to transform the original graph into corresponding line graphs, presenting edge information in the form of node features, effectively capturing the global structural information of the graph.
As a self-supervised learning technique, aims to acquire meaningful representations of node features by discerning similarities and differences among samples.
Dec 13, 2023 · Based on this insight, We propose Line Graph Contrastive Learning (LineGCL), a novel graph contrastive learning framework that effectively ...
Jul 18, 2024 · LineGCL utilizes the characteristics of line graphs to transform the original graph into corresponding line graphs, presenting edge information ...
Oct 25, 2022 · Most existing researches measure the likelihood of links by different similarity scores on node pairs and predict links between nodes. However, ...
The linear SVM is trained by applying cross validation on training data folds and the best mean accuracy is reported. For node classification, we report the ...
Line Graph Contrastive Learning for Node Classification. https://doi.org/10.2139/ssrn.4663055. Journal: 2023. Publisher: Elsevier BV. Authors: mingyuan Li; lei ...
People also ask
What is node classification in GNN?
How to do graph classification?
How to use graph neural network for text classification?
Feb 14, 2024 · In this work, we propose a novel and robust GNN encoder, Low-Rank Graph Contrastive Learning (LR-GCL). Our method performs transductive node ...
Graph contrastive learning (GCL) has attracted a surge of attention due to its superior performance for learning node/graph representations without labels.
Deep graph representation learning, which aims to learn a low-dimensional dense vector that encodes node structures and attributes, enables efficient feature ...