Tensor Decompositions for temporal knowledge base completion
This addresses the need for temporal link prediction in evolving knowledge bases, which is incremental as it builds on existing static methods.
The paper tackles the problem of link prediction in temporal knowledge bases, such as answering queries like (US, has president, ?, 2012), by proposing a solution based on tensor decomposition and an extension of ComplEx, achieving state-of-the-art performance. It also introduces a new, larger dataset from Wikidata for evaluating temporal and non-temporal methods.
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.