Tensor Decompositions for temporal knowledge base completion

By Timothée Lacroix, Guillaume Obozinski, Nicolas Usunier. International Conference on Learning Representations, 2020

362 citations recorded by the source corpus.

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 of the form (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 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.

Subfields: Artificial Intelligence, Computational Mathematics

View Paper: https://www.semanticscholar.org/paper/b6263f7ab737c7a790dbf818a1bb2255449db6e8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mathematics

Citations in the corpus

A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “u et al. [155] proposed context selection to capture useful contexts, and measured temporal consistency with selected context. By formulating temporal KGC as 4-order tensor completion, Lacroix et al. [156] proposed TComplEx, which extends ComplEx decomposition, and introduced weighted regularizers. ”
A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, background): “Many temporal knowledge graph completion models use canonical polyadic decomposition, e.g., [332] and [333].”
Question Answering Over Temporal Knowledge Graphs (2021, methodology): “Several such Temporal KGs have been proposed in the literature, where the focus is on KG completion (Dasgupta et al. 2018; Garcı́a-Durán et al. 2018; Leetaru and Schrodt 2013; Lacroix et al. 2020; Jain et al. 2020).”
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “For example, TComplEx and TNTComplEx [167] both come from ComplEx, where the fourth-order tensor space with additional consideration of time information is modeled by them.”
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks (2020, background): “…latent representations for each snapshot separately, and thus are not capable of capturing the long-term dependency of facts in consecutive time snapshots (Jiang et al. 2016; Dasgupta, Ray, and Talukdar 2018; Wang and Li 2019; Ma, Tresp, and Daxberger 2019; Lacroix, Obozinski, and Usunier 2019).”
Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs (2019, methodology): “…attempts on incorporating temporal information in modeling dynamic knowledge graphs, broadly categorized into two settings - extrapolation (Trivedi et al., 2017) and interpolation (Garc´ıa-Dur´an et al., 2018; Leblay and Chekol, 2018; Dasgupta et al., 2018; Goel et al., 2020; Lacroix et al., 2020).”