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 2403.10231cs.LGcs.AIcs.SI
收藏

少即是多:大规模知识图谱上的单样本子图推理

Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs

Hong Kong Baptist University(香港浸会大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学)

Zhanke Zhou, Yongqi Zhang, Jiangchao Yao, Quanming Yao, Bo Han

AI总结:

针对现有知识图谱链接预测因依赖全图导致的可扩展性问题,提出单样本子图链接预测方法,通过PPR提取查询相关子图并在其上预测,结合最优配置自动搜索,在五个大规模基准上实现效率提升与领先性能。

摘要:

为在知识图谱(KG)上推导新事实,链接预测器需从图结构中学习并收集局部证据以找到给定查询的答案。然而,现有方法因利用整个KG进行预测而存在严重的可扩展性问题,这阻碍了它们在大规模KG上的应用前景,且无法通过普通采样方法直接解决。在本研究中,我们提出单样本子图链接预测以实现高效且自适应的预测。设计原则是,预测过程不直接作用于整个KG,而是解耦为两步:(i)根据查询仅提取一个子图;(ii)在该单一、依赖查询的子图上进行预测。我们发现,非参数且计算高效的启发式算法Personalized PageRank(PPR,个性化页面排名)能有效识别潜在答案和支持证据。借助高效的基于子图的预测,我们进一步引入了数据空间和模型空间中最优配置的自动搜索。实验表明,我们在五个大规模基准数据集上实现了效率提升和领先性能。代码公开于:https://github.com/tmlr-group/one-shot-subgraph。

英文摘要:

To deduce new facts on a knowledge graph (KG), a link predictor learns from the graph structure and collects local evidence to find the answer to a given query. However, existing methods suffer from a severe scalability problem due to the utilization of the whole KG for prediction, which hinders their promise on large scale KGs and cannot be directly addressed by vanilla sampling methods. In this work, we propose the one-shot-subgraph link prediction to achieve efficient and adaptive prediction. The design principle is that, instead of directly acting on the whole KG, the prediction procedure is decoupled into two steps, i.e., (i) extracting only one subgraph according to the query and (ii) predicting on this single, query dependent subgraph. We reveal that the non-parametric and computation-efficient heuristics Personalized PageRank (PPR) can effectively identify the potential answers and supporting evidence. With efficient subgraph-based prediction, we further introduce the automated searching of the optimal configurations in both data and model spaces. Empirically, we achieve promoted efficiency and leading performances on five large-scale benchmarks. The code is publicly available at: https://github.com/tmlr-group/one-shot-subgraph.

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。

↑