OGB-LSC：图上机器学习的大规模挑战
OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
摘要：
在大规模图形数据上实现有效和高效的机器学习（ML）（例如，具有数十亿条边的图）可以对工业和科学应用两者产生巨大影响。然而，现有的推进大规模图ML的努力在很大程度上受到缺乏合适的公共基准的限制。在这里，我们提出了OGB大规模挑战（OGB-LSC），这是三个真实世界数据集的集合，用于促进大规模图ML的进步。OGB-LSC数据集比现有数据集大几个数量级，涵盖了三个核心图学习任务-链接预测、图回归和节点分类。此外，我们还提供了专门的基线实验，将表达图ML模型扩展到大规模数据集。我们发现，表达模型的表现明显优于简单的可扩展基线，这表明有机会致力于进一步大规模改进图ML。此外，OGB-LSC数据集在ACM KDD Cup 2021上部署，并吸引了全球500多支球队注册，在此期间，通过各种创新技术实现了显着的性能提升。我们总结了获奖解决方案使用的常见技术，并强调了大规模图ML的当前最佳实践。最后，我们描述了我们如何在KDD杯之后更新数据集，以进一步促进研究进展。OGB-LSC数据集、基线代码和有关KDD Cup的所有信息都可以在https://ogb.stanford.edu/docs/lsc/上找到。
英文摘要：
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/ .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
