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

TL;DR

The paper introduces OGB-LSC, a set of large-scale graph datasets for advancing machine learning on graphs, accompanied by baseline models, and reports on its success in a major competition to foster innovation.

Contribution

It provides the first large-scale, real-world graph datasets for ML, along with baseline experiments and insights from a global competition to accelerate research.

Findings

Expressive models outperform simple baselines on large datasets.

Participation in KDD Cup led to significant performance improvements.

The datasets and benchmarks are now publicly available for research.

Abstract

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/ .