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.
( Image credit: Hierarchical Graph Pooling with Structure Learning )
Papers
Showing 1–10 of 927 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | U2GNN (Unsupervised) | Accuracy | 89.2 | — | Unverified |
| 2 | TFGW ADJ (L=2) | Accuracy | 56.8 | — | Unverified |
| 3 | TREE-G | Accuracy | 56.4 | — | Unverified |
| 4 | MEWISPool | Accuracy | 56.23 | — | Unverified |
| 5 | DUGNN | Accuracy | 56.1 | — | Unverified |
| 6 | G_ResNet | Accuracy | 54.53 | — | Unverified |
| 7 | sGIN | Accuracy | 54.52 | — | Unverified |
| 8 | GIUNet | Accuracy | 54 | — | Unverified |
| 9 | U2GNN | Accuracy | 53.6 | — | Unverified |
| 10 | SEG-BERT | Accuracy | 53.4 | — | Unverified |