OGB (Open Graph Benchmark)

Introduced by Hu et al. in Open Graph Benchmark: Datasets for Machine Learning on Graphs

The Open Graph Benchmark (OGB) is a collection of realistic, large-scale, and diverse benchmark datasets for machine learning on graphs. OGB datasets are automatically downloaded, processed, and split using the OGB Data Loader. The model performance can be evaluated using the OGB Evaluator in a unified manner. OGB is a community-driven initiative in active development.

Source: https://ogb.stanford.edu/

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Node Property Prediction	ogbn-arxiv	SimTeG+TAPE+RevGAT
Node Property Prediction	ogbn-products	GLEM+EnGCN
Graph Property Prediction	ogbg-molhiv	PAS+FPs
Node Property Prediction	ogbn-mag	RpHGNN+LP+CR
Graph Property Prediction	ogbg-molpcba	HyperFusino
Link Property Prediction	ogbl-collab	E2N
Link Property Prediction	ogbl-wikikg2	RelEns
Link Property Prediction	ogbl-ddi	ELGNN
Node Property Prediction	ogbn-proteins	LD+GAT
Link Property Prediction	ogbl-ppa	SIEG
Link Property Prediction	ogbl-citation2	CFG
Node Property Prediction	ogbn-papers100M	GLEM+GIANT+GAMLP
Graph Property Prediction	ogbg-code2	SAT++ with Magnetic Laplacian
Link Property Prediction	ogbl-biokg	RelEns
Graph Property Prediction	ogbg-ppa	PAS+F2GNN
Link Prediction	ogbl-collab	Edge2Node