KDD Cup 2021 OGB-LSC WikiKG90M-LSC赛道GraphMIRAcles队技术报告
Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021
摘要:
大规模知识图谱中的链接预测问题近年来受到越来越多的关注。OGB-LSC团队提出了OGB大规模挑战(OGB-LSC),这是三个真实世界数据集的集合,用于推进大规模图机器学习的最新技术。本文介绍了我们团队GraphMIRAcles在2021年OGB-LSC@KDD Cup的WikiKG90M-LSC赛道上的解决方案。在WikiKG90 M-LSC轨道中,目标是自动预测WikiKG90 M中的缺失链接,WikiKG90 M是从Wikidata中提取的大规模知识图谱。为了解决这一挑战,我们提出了一个框架,它集成了三个组件-一个基本模型ComplEx-CMRC,规则挖掘机AMIE 3,和一个推理模型来预测丢失的链接。实验表明,我们的解决方案在测试数据集上实现了0.9707的MRR。此外,由于推理模型中的知识蒸馏使用测试尾候选者-这在实践中是不可用的-我们进行消融研究知识蒸馏。实验表明,我们的模型没有知识蒸馏达到了0.9533的MRR的完整验证数据集。
英文摘要:
Link prediction in large-scale knowledge graphs has gained increasing attention recently. The OGB-LSC team presented OGB Large-Scale Challenge (OGB-LSC), a collection of three real-world datasets for advancing the state-of-the-art in large-scale graph machine learning. In this paper, we introduce the solution of our team GraphMIRAcles in the WikiKG90M-LSC track of OGB-LSC @ KDD Cup 2021. In the WikiKG90M-LSC track, the goal is to automatically predict missing links in WikiKG90M, a large scale knowledge graph extracted from Wikidata. To address this challenge, we propose a framework that integrates three components -- a basic model ComplEx-CMRC, a rule miner AMIE 3, and an inference model to predict missing links. Experiments demonstrate that our solution achieves an MRR of 0.9707 on the test dataset. Moreover, as the knowledge distillation in the inference model uses test tail candidates -- which are unavailable in practice -- we conduct ablation studies on knowledge distillation. Experiments demonstrate that our model without knowledge distillation achieves an MRR of 0.9533 on the full validation dataset.
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。