Tensor Decompositions for temporal knowledge base completion

Abstract

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.

References in corpus (2)

• A Review of Relational Machine Learning for Knowledge Graphs
• Learning with the Weighted Trace-norm under Arbitrary Sampling Distributions

Cited by in corpus (14)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Temporal Knowledge Graph Completion: A Survey
• Time-aware Graph Neural Networks for Entity Alignment between Temporal Knowledge Graphs
• Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs
• Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
• Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion
• Temporal Knowledge Graph Forecasting with Neural ODE
• xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links
• TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs
• TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
• T-GAP: Learning to Walk across Time for Temporal Knowledge Graph Completion
• DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
• RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion
• TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting