OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs

17 Mar 2021  ·  Weihua Hu, Matthias Fey, Hongyu Ren, Maho Nakata, Yuxiao Dong, Jure Leskovec ·

Enabling effective and efficient machine learning (ML) over large-scale graph data (e.g., graphs with billions of edges) can have a great impact on both industrial and scientific applications. However, existing efforts to advance large-scale graph ML have been largely limited by the lack of a suitable public benchmark. Here we present OGB Large-Scale Challenge (OGB-LSC), a collection of three real-world datasets for facilitating the advancements in large-scale graph ML. The OGB-LSC datasets are orders of magnitude larger than existing ones, covering three core graph learning tasks -- link prediction, graph regression, and node classification. Furthermore, we provide dedicated baseline experiments, scaling up expressive graph ML models to the massive datasets. We show that expressive models significantly outperform simple scalable baselines, indicating an opportunity for dedicated efforts to further improve graph ML at scale. Moreover, OGB-LSC datasets were deployed at ACM KDD Cup 2021 and attracted more than 500 team registrations globally, during which significant performance improvements were made by a variety of innovative techniques. We summarize the common techniques used by the winning solutions and highlight the current best practices in large-scale graph ML. Finally, we describe how we have updated the datasets after the KDD Cup to further facilitate research advances. The OGB-LSC datasets, baseline code, and all the information about the KDD Cup are available at https://ogb.stanford.edu/docs/lsc/ .

PDF Abstract


Introduced in the Paper:


Used in the Paper:


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification MAG240M-LSC SIGN Validation Accuracy 66.64 # 5
Test Accuracy 66.09 # 5
Node Classification MAG240M-LSC GraphSAGE (NS) Validation Accuracy 67.32 # 4
Test Accuracy 66.25 # 4
Node Classification MAG240M-LSC GAT (NS) Validation Accuracy 67.71 # 3
Test Accuracy 66.63 # 3
Node Classification MAG240M-LSC R-GraphSAGE (NS) Validation Accuracy 70.21 # 2
Test Accuracy 68.94 # 2
Node Classification MAG240M-LSC R-GAT (NS) Validation Accuracy 70.48 # 1
Test Accuracy 69.49 # 1
Graph Regression PCQM4M-LSC GCN-Virtual Validation MAE 0.151 # 5
Test MAE 15.79 # 3
Graph Regression PCQM4M-LSC MLP-fingerprint Validation MAE 0.2044 # 7
Test MAE 20.68 # 6
Graph Regression PCQM4M-LSC GCN Validation MAE 0.1684 # 6
Test MAE 18.38 # 5
Graph Regression PCQM4M-LSC GIN Test MAE 16.78 # 4
Graph Regression PCQM4M-LSC GIN-virtual Validation MAE 0.1396 # 4
Test MAE 14.87 # 2
Knowledge Graphs WikiKG90M-LSC ComplEx-Concat Validation MRR 0.8425 # 2
Test MRR 0.8637 # 2
Knowledge Graphs WikiKG90M-LSC ComplEx-RoBERTa Validation MRR 0.7052 # 3
Test MRR 0.7186 # 3
Knowledge Graphs WikiKG90M-LSC TransE-RoBERTa Validation MRR 0.6039 # 4
Test MRR 0.6288 # 4
Knowledge Graphs WikiKG90M-LSC TransE-Concat Validation MRR 0.8494 # 1
Test MRR 85.48 # 1


No methods listed for this paper. Add relevant methods here