arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2206.04798cs.AIcs.LG
收藏

A*Net:一种可扩展的基于路径的知识图谱推理方法

A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs

Mila - Québec AI Institute(魁北克人工智能研究所);University of Montréal(蒙特利尔大学);Intel AI Lab(英特尔人工智能实验室);Peking University(北京大学);LG Electronics AI Lab(LG电子人工智能实验室);HEC Montréal(蒙特利尔高等商学院);CIFAR AI Chair(CIFAR人工智能讲席)

Zhaocheng Zhu, Xinyu Yuan, Mikhail Galkin, Sophie Xhonneux, Ming Zhang, Maxime Gazeau, Jian Tang

AI总结:

针对基于路径的知识图谱推理方法可扩展性不足的问题,提出受A*算法启发的A*Net,通过优先级函数选择重要节点边以降低开销,在基准上性能媲美现有最优路径方法,在百万级数据集上取得新SOTA且收敛更快。

摘要:

大规模知识图谱推理长期以来一直由嵌入方法主导。虽然基于路径的方法具备嵌入方法所缺乏的归纳能力,但其可扩展性受限于路径数量呈指数级增长的问题。本文提出A*Net,一种可扩展的基于路径的知识图谱推理方法。受求解最短路径问题的A*算法启发,我们的A*Net学习一个优先级函数,在每次迭代中选择重要的节点和边,以降低训练和推理阶段的时间与内存占用。可指定所选节点和边的比例,在性能与效率之间进行权衡。在直推式和归纳式知识图谱推理基准上的实验表明,A*Net取得了与现有最先进的基于路径的方法相当的性能,而每次迭代仅访问10%的节点和10%的边。在百万级规模数据集ogbl-wikikg2上,A*Net不仅取得了新的最优结果,收敛速度也快于嵌入方法。A*Net是首个能在此等规模下开展知识图谱推理的基于路径的方法。

英文摘要:

Reasoning on large-scale knowledge graphs has been long dominated by embedding methods. While path-based methods possess the inductive capacity that embeddings lack, their scalability is limited by the exponential number of paths. Here we present A*Net, a scalable path-based method for knowledge graph reasoning. Inspired by the A* algorithm for shortest path problems, our A*Net learns a priority function to select important nodes and edges at each iteration, to reduce time and memory footprint for both training and inference. The ratio of selected nodes and edges can be specified to trade off between performance and efficiency. Experiments on both transductive and inductive knowledge graph reasoning benchmarks show that A*Net achieves competitive performance with existing state-of-the-art path-based methods, while merely visiting 10% nodes and 10% edges at each iteration. On a million-scale dataset ogbl-wikikg2, A*Net not only achieves a new state-of-the-art result, but also converges faster than embedding methods. A*Net is the first path-based method for knowledge graph reasoning at such scale.

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。

↑