paper-with-me

OGB

Open Graph Benchmark

홈페이지 · 논문 1,000편

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

Graphs

벤치마크

Node Property Prediction on ogbn-arxiv 결과 86개

Node Property Prediction on ogbn-products 결과 64개

Graph Property Prediction on ogbg-molhiv 결과 43개

Node Property Prediction on ogbn-mag 결과 39개

Graph Property Prediction on ogbg-molpcba 결과 36개

Link Property Prediction on ogbl-collab 결과 34개

Link Property Prediction on ogbl-ddi 결과 31개

Link Property Prediction on ogbl-wikikg2 결과 30개

Link Property Prediction on ogbl-ppa 결과 26개

Node Property Prediction on ogbn-proteins 결과 26개

Link Property Prediction on ogbl-citation2 결과 23개

Graph Property Prediction on ogbg-code2 결과 21개

Node Property Prediction on ogbn-papers100M 결과 20개

Graph Property Prediction on ogbg-ppa 결과 18개

Link Property Prediction on ogbl-biokg 결과 16개

Link Prediction on ogbl-collab 결과 1개

Node Classification on ogbn-products 결과 1개