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 | TFGW ADJ (L=2) | Accuracy | 88.1 | — | Unverified |
| 2 | WKPI-kmeans | Accuracy | 87.2 | — | Unverified |
| 3 | FGW wl h=4 sp | Accuracy | 86.42 | — | Unverified |
| 4 | WL-OA | Accuracy | 86.1 | — | Unverified |
| 5 | WL-OA Kernel | Accuracy | 86.1 | — | Unverified |
| 6 | FGW wl h=2 sp | Accuracy | 85.82 | — | Unverified |
| 7 | WWL | Accuracy | 85.75 | — | Unverified |
| 8 | DUGNN | Accuracy | 85.5 | — | Unverified |
| 9 | δ-2-LWL | Accuracy | 85.5 | — | Unverified |
| 10 | CIN++ | Accuracy | 85.3 | — | Unverified |