Tensor Decompositions for temporal knowledge base completion

• DOI: 10.48550/arxiv.2004.04926
• Publication Date: 2020-01-01
• Authors: Timothée Lacroix; Guillaume Obozinski; Nicolas Usunier
• Keywords: Regularization; Link (geometry); Base (topology); Representation

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