Accuracy(10-fold): 81.13
Papers with Code · CC BY-SA 4.0
Graph Classification
Graph Classification is a task that involves classifying a graph-structured data into different classes or categories. Graphs are a powerful way to represent relationships and interactions between different entities, and graph classification can be applied to a wide range of applications, such as social network analysis, bioinformatics, and recommendation systems. In graph classification, the input is a graph, and the goal is to learn a classifier that can accurately predict the class of the graph.
<span style="color:grey; opacity: 0.6">( Image credit: Hierarchical Graph Pooling with Structure Learning )</span>
논문
Accuracy: 49.75%
Accuracy: 96.41%
Accuracy: 86.250±0.957
Accuracy: 52.88%
Accuracy: 41.27%
Accuracy: 77.500±2.646
Accuracy: 84.250±2.062
Accuracy: 52.11%
Accuracy: 76%
Accuracy: 80.000±2.739
Accuracy: 57.22%
Accuracy(10-fold): 75.21
Accuracy: 78.70%
Accuracy: 82.13%
Accuracy: 77.94%
Accuracy(10-fold): 78.11
Accuracy: 78.000±3.808
Accuracy: 80.250±3.304
Accuracy: 79.250±3.096
Accuracy: 77.2%
Accuracy: 79.500±3.109
Accuracy: 78.3%
Accuracy: 55.1%
Accuracy: 76.6%
Accuracy: 79.90%