Accuracy: 89.41 ± 4.74
Papers with Code · CC BY-SA 4.0
Node Classification
Node Classification is a machine learning task in graph-based data analysis, where the goal is to assign labels to nodes in a graph based on the properties of nodes and the relationships between them.
Node Classification models aim to predict non-existing node properties (known as the target property) based on other node properties. Typical models used for node classification consists of a large family of graph neural networks. Model performance can be measured using benchmark datasets like Cora, Citeseer, and Pubmed, among others, typically using Accuracy and F1.
<span style="color:grey; opacity: 0.6">( Image credit: Fast Graph Representation Learning With PyTorch Geometric )</span>
논문
Accuracy: 66.36±0.11
Accuracy: 66.06±0.19
Accuracy: 19.1%Macro-F1: 0.1552
Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection
Macro F1: 15.97Micro F1: 53.24
Accuracy: 86.33 ± 0.17
AUC: 41.12%
Accuracy: 19.4%Macro-F1: 0.183
Accuracy: 92.54±3.70
Accuracy: 83.05±0.07
Micro-F1: 0.381
Accuracy: 82.83±0.04
Accuracy: 93.72 ± 4.59
Accuracy: 21.3%Macro-F1: 0.194
Accuracy: 90.00±2.97
Accuracy: 88.82 ± 3.40
Accuracy: 94.99±0.65
Accuracy: 86.46 ± 0.09
Accuracy: 17.50%Macro-F1: 0.164
Accuracy: 86.10±0.05
Accuracy: 88.63±4.54
Accuracy: 88.73±4.47
Accuracy: 89.01 ± 4.1
Accuracy: 21.10%Macro-F1: 0.190
Accuracy: 88.77