Diachronic Embedding for Temporal Knowledge Graph Completion

By Rishab Goel, Seyed Mehran Kazemi, Marcus A. Brubaker, Pascal Poupart. AAAI Conference on Artificial Intelligence, 2019

445 citations recorded by the source corpus.

Knowledge graphs (KGs) typically contain temporal facts indicating relationships among entities at different times. Due to their incompleteness, several approaches have been proposed to infer new facts for a KG based on the existing ones–a problem known as KG completion. KG embedding approaches have proved effective for KG completion, however, they have been developed mostly for static KGs. Developing temporal KG embedding models is an increasingly important problem. In this paper, we build novel models for temporal KG completion through equipping static models with a diachronic entity embedding function which provides the characteristics of entities at any point in time. This is in contrast to the existing temporal KG embedding approaches where only static entity features are provided. The proposed embedding function is model-agnostic and can be potentially combined with any static model. We prove that combining it with SimplE, a recent model for static KG embedding, results in a fully expressive model for temporal KG completion. Our experiments indicate the superiority of our proposal compared to existing baselines.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/e70bcd320f96bf1b20f9102cb1db4725ecf903f5

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

Representation Learning for Dynamic Graphs: A Survey (2019, methodology): “The interpolation problem is also known as the completion problem and is mainly used for completing (dynamic) KGs (Jiang et al. (2016); Leblay and Chekol (2018); Garćıa-Durán et al. (2018); Dasgupta et al. (2018); Goel et al. (2020)).”
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, methodology): “[158] took an entity and timestamp as the input of entity embed-”
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).”
Question Answering Over Temporal Knowledge Graphs (2021, background): “Temporal KG embeddings are another upcoming area where entities, relations and timestamps in a temporal KG are embedded in a low-dimensional vector space (Dasgupta et al. 2018, Lacroix et al. 2020, Jain et al. 2020, Goel et al. 2019).”
Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, methodology): “i, jjZjj F Norm iof z, and Frobenius norm of Z. A 0;z Transpose of a matrix and a vector Table 1: Summary of the main notation and abbreviations. Garca-Duran et al. (2018); Dasgupta et al. (2018); Goel et al. (2020)). An example of the interpolation problem is to predict which country won the world ”
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, methodology): “Meanwhile, Diachronic [175] map entity and relation embeddings, paired with temporal information, into a KGR model space, thus deﬁning a framework yielding speciﬁc models such as DE-TransE and DE-SimplE.”
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks (2020, methodology): “DE-SimplE (Goel et al. 2020) leverages diachronic embeddings to represent entities at different timestamps and employs the same score function as SimplE (Kazemi and Poole 2018) to score the plausibility of a quadruple.”
Tensor Decompositions for temporal knowledge base completion (2020, methodology): “The GDelt dataset described in Ma et al. (2018); Goel et al. (2020) holds many triples ( 2 M ), but does not describe enough entities ( 500 ).”
Temporal Graph Networks for Deep Learning on Dynamic Graphs (2020, background): “Other recent works have focused on dynamic knowledge graphs [21, 65, 12, 19].”