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 2004.04926stat.MLcs.LG
收藏

时态知识库完备化的张量分解

Tensor Decompositions for temporal knowledge base completion

Université Paris-Est(巴黎东大学);Ecole des Ponts ParisTech(巴黎高科桥路学院);Facebook AI Research(Facebook人工智能研究院);Swiss Data Science Center(瑞士数据科学中心);EPFL(洛桑联邦理工学院);ETH Zürich(苏黎世联邦理工学院)

Timothée Lacroix, Guillaume Obozinski, Nicolas Usunier

摘要:

大多数关系数据中的表示学习和链接预测算法都是针对静态数据设计的。然而,它们所应用的数据通常会随着时间的推移而演变,例如社交网络中的朋友图或推荐系统中的用户与项目的交互。这也是知识库的情况,它包含的事实,如(美国,有总统,B。奥巴马,[2009-2017]),仅在某些时间点有效。对于时间约束下的链路预测问题,即,回答诸如(US,has president,?,2012),我们提出了一个解决方案的灵感来自4阶张量的典型分解。我们引入了新的正则化方案并提出了ComplEx的扩展(Trouillon等人,2016年),实现了最先进的性能。此外,我们提出了一个新的数据集的知识库完成从维基数据,大于以前的基准由一个数量级,作为一个新的参考评估时间和非时间的链接预测方法。

英文摘要:

Most algorithms for representation learning and link prediction in relational data have been designed for static data. However, the data they are applied to usually evolves with time, such as friend graphs in social networks or user interactions with items in recommender systems. This is also the case for knowledge bases, which contain facts such as (US, has president, B. Obama, [2009-2017]) that are valid only at certain points in time. For the problem of link prediction under temporal constraints, i.e., answering queries such as (US, has president, ?, 2012), we propose a solution inspired by the canonical decomposition of tensors of order 4. We introduce new regularization schemes and present an extension of ComplEx (Trouillon et al., 2016) that achieves state-of-the-art performance. Additionally, we propose a new dataset for knowledge base completion constructed from Wikidata, larger than previous benchmarks by an order of magnitude, as a new reference for evaluating temporal and non-temporal link prediction methods.

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。

↑