IMDB-BINARY is a movie collaboration dataset that consists of the ego-networks of 1,000 actors/actresses who played roles in movies in IMDB. In each graph, nodes represent actors/actress, and there is an edge between them if they appear in the same movie. These graphs are derived from the Action and Romance genres.
Source: A simple yet effective baseline for non-attributed graph classification
Variants: IMDb-B, IMDB-BINARY
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Graph Classification | R-GCN + PANDA | PANDA: Expanded Width-Aware Message Passing … | 2024-06-06 |
| Graph Classification | GIN + PANDA | PANDA: Expanded Width-Aware Message Passing … | 2024-06-06 |
| Graph Classification | R-GIN + PANDA | PANDA: Expanded Width-Aware Message Passing … | 2024-06-06 |
| Graph Classification | GCN + PANDA | PANDA: Expanded Width-Aware Message Passing … | 2024-06-06 |
| Graph Classification | Local Topological Profile (LTP) | Strengthening structural baselines for graph … | 2023-05-01 |
| Graph Classification | GAP-Layer (Ncut) | DiffWire: Inductive Graph Rewiring via … | 2022-06-15 |
| Graph Classification | CT-Layer | DiffWire: Inductive Graph Rewiring via … | 2022-06-15 |
| Graph Classification | GAP-Layer (Rcut) | DiffWire: Inductive Graph Rewiring via … | 2022-06-15 |
Recent papers with results on this dataset: