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 801–825 of 927 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | GIN-0 | Accuracy | 762 | — | Unverified |
| 2 | HGP-SL | Accuracy | 84.91 | — | Unverified |
| 3 | rLap (unsupervised) | Accuracy | 84.3 | — | Unverified |
| 4 | TFGW ADJ (L=2) | Accuracy | 82.9 | — | Unverified |
| 5 | FIT-GNN | Accuracy | 82.1 | — | Unverified |
| 6 | DUGNN | Accuracy | 81.7 | — | Unverified |
| 7 | MEWISPool | Accuracy | 80.71 | — | Unverified |
| 8 | CIN++ | Accuracy | 80.5 | — | Unverified |
| 9 | MAGPool | Accuracy | 80.36 | — | Unverified |
| 10 | SAEPool | Accuracy | 80.36 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Evolution of Graph Classifiers | Accuracy | 100 | — | Unverified |
| 2 | MEWISPool | Accuracy | 96.66 | — | Unverified |
| 3 | TFGW ADJ (L=2) | Accuracy | 96.4 | — | Unverified |
| 4 | GIUNet | Accuracy | 95.7 | — | Unverified |
| 5 | G_Inception | Accuracy | 95 | — | Unverified |
| 6 | GIC | Accuracy | 94.44 | — | Unverified |
| 7 | CIN++ | Accuracy | 94.4 | — | Unverified |
| 8 | sGIN | Accuracy | 94.14 | — | Unverified |
| 9 | CAN | Accuracy | 94.1 | — | Unverified |
| 10 | Deep WL SGN(0,1,2) | Accuracy | 93.68 | — | Unverified |
| # | 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 Kernel | Accuracy | 86.1 | — | Unverified |
| 5 | WL-OA | 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 |