Learning Sequence Encoders for Temporal Knowledge Graph Completion

By Alberto García-Durán, Sebastijan Dumancic, Mathias Niepert. 2018

557 citations recorded by the source corpus.

Research on link prediction in knowledge graphs has mainly focused on static multi-relational data. In this work we consider temporal knowledge graphs where relations between entities may only hold for a time interval or a specific point in time. In line with previous work on static knowledge graphs, we propose to address this problem by learning latent entity and relation type representations. To incorporate temporal information, we utilize recurrent neural networks to learn time-aware representations of relation types which can be used in conjunction with existing latent factorization methods. The proposed approach is shown to be robust to common challenges in real-world KGs: the sparsity and heterogeneity of temporal expressions. Experiments show the benefits of our approach on four temporal KGs. The data sets are available under a permissive BSD-3 license.

Subfields: Artificial Intelligence, Management Science and Operations Research

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 Management Science and Operations Research

Citations in the corpus

Recurrent Event Network for Reasoning over Temporal Knowledge Graphs (2019, methodology): “Recent studies on TKG reasoning focus on embedding time expressions into low-dimensional space [9, 6, 13].”
Question Answering Over Temporal Knowledge Graphs (2021, background): “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).”
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks (2020, methodology): “TA-DistMult (Garc´ıa-Dur´an, Dumancic, and Niepert 2018) utilize recurrent neural networks to learn time-aware representations of relations and uses standard scoring functions from TransE and DistMult.”
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, methodology): “[154] concatenated predicate token sequence and temporal token sequence, and used LSTM to encode the concatenated time-aware predicate sequences.”
Temporal Graph Networks for Deep Learning on Dynamic Graphs (2020, background): “Other recent works have focused on dynamic knowledge graphs (Goel et al., 2019; Xu et al., 2019; Dasgupta et al., 2018; García-Durán et al., 2018).”
Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs (2019, methodology): “In the interpolation setting, new facts are predicted for time t such that t 0 ≤ t ≤ t T (Garc´ıa-Dur´an et al., 2018; Leblay and Chekol, 2018; Das-gupta et al., 2018).”
Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, methodology): “Instead of relying on an encoder that maps each timestamp to a vector representation, García-Durán et al. [77] assume the encoder provides an embedding for each character in the timestamp.”