论文标题
时间知识库完成的张量分解
Tensor Decompositions for temporal knowledge base completion
论文作者
论文摘要
用于表示学习和链接预测的大多数关系数据中的算法都是为静态数据设计的。但是，它们被应用于通常随时间发展的数据，例如社交网络中的朋友图或用户与推荐系统中的项目进行交互。对于知识库也是如此，其中包含（我们的总统，B。Obama，[2009-2017]）等事实，仅在某些时间点有效。对于在时间约束下的链接预测问题，即回答诸如（我们的总统，？，2012年）之类的查询，我们提出了一种以4的规定分解为4的解决方案。我们引入了新的正则化计划并介绍了复杂的扩展（Trouillon等人，2016年），以实现The-Ar-Ar-Art The-Art the-Art-Art-Art-Art-Art-Art the-Art the-Art the-art the-art the-art绩效。此外，我们为通过Wikidata构建的知识库完成的新数据集提出了比以前的基准测量级的数量级大的数据集，作为评估时间和非时空链接预测方法的新参考。
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.
