Other Graph Benchmarks

MovieLens Film

Node Classification

Structure

1Graphs
18,352Nodes
1,104,162Edges
9Classes
1000Node Feature Dim

Coverage

9-class node classification on a MovieLens/IMDb movie graph, predicting one or more of nine genre labels per film; this is not the Actor/Film dataset. Evaluated by Micro-F1.

Dataset details

Task

Movie graph with genre labels from the MovieLens/IMDb film benchmark; distinct from the five-class Actor graph sometimes called Film. The primary catalog metric is Micro-F1.

Data

Movie graph with genre labels from the MovieLens/IMDb film benchmark; distinct from the five-class Actor graph sometimes called Film. The cataloged artifact reports 1 graphs, 9 target classes or tasks.

Features

Input construction is dataset-specific and follows the cited release: program call graphs, 3D point coordinates, text-derived vectors, product attributes, or movie metadata. Added edges, neighborhood graphs, and feature normalization are preprocessing choices.

Splits and evaluation

The catalog records these protocols or variants: Standard split. Evaluation uses Micro-F1 (higher is better). Exact masks or folds must come from the cited release.

Quirks and pitfalls

These entries come from unrelated upstream benchmarks and have no shared protocol. Report the exact graph construction, split, feature pipeline, and label granularity; similarly named Film, Actor, IMDB, or Amazon artifacts are not interchangeable.

Sources

MovieLens/IMDb film graph used by Bruna et al. 2016.

SOTA Progression

new SOTA matches SOTA at that time other proposed result other baseline result

Leaderboard

#ModelMicro-F1 ↑Paper
1
CLN-HWN-mini
0.5750
2
CLN-HWN-full
0.5740
3
CLN-FNN
0.5430
4
SL-LR
0.5340
5
HWN-noRel
0.5080
6
nbC-IC
0.4660
7
nbC-RL
0.4350
SOTA performance set a new SOTA at the time matched the SOTA at the time