HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding

By Shib Sankar Dasgupta, Swayambhu Nath Ray, Partha P. Talukdar. 2018

493 citations recorded by the source corpus.

Knowledge Graph (KG) embedding has emerged as an active area of research resulting in the development of several KG embedding methods. Relational facts in KG often show temporal dynamics, e.g., the fact (Cristiano_Ronaldo, playsFor, Manchester_United) is valid only from 2003 to 2009. Most of the existing KG embedding methods ignore this temporal dimension while learning embeddings of the KG elements. In this paper, we propose HyTE, a temporally aware KG embedding method which explicitly incorporates time in the entity-relation space by associating each timestamp with a corresponding hyperplane. HyTE not only performs KG inference using temporal guidance, but also predicts temporal scopes for relational facts with missing time annotations. Through extensive experimentation on temporal datasets extracted from real-world KGs, we demonstrate the effectiveness of our model over both traditional as well as temporal KG embedding methods.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

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 Statistical and Nonlinear Physics

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].”
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).”
Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning (2021, methodology): “HyTE [4], TTransE [21] and TA-DistMult [9] are selected as the temporal models under the interpolation setting.”
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, unknown): “For instance, HyTE [202] represents each timestamp as a learnable hyper-plane in the embedding space, then projects entity and relation embeddings into the hyper-plane and utilizes the TransE scoring function on the projections.”
Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, methodology): “Dasgupta et al. [54] ordered the predicted timestamps in the decreasing order of their probabilities and selected the rank associated with the correct timestamp.”
A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, background): “HyTE [329] treats the timestamp as a hyperplane for matching entity and relation embeddings.”
Diachronic Embedding for Temporal Knowledge Graph Completion (2019, background): “Recent work has shown a substantial boost in performance by extending these approaches to utilize time [6, 3, 13, 4].”
Revisiting Evaluation of Knowledge Base Completion Models (2020, background): “…prediction task, include tensor multiplication [Nickel et al., 2011, Socher et al., 2013, Yang et al., 2015, Balaževi´c et al., 2019], algebraic operations [Bordes et al., 2011, 2013b, Dasgupta et al., 2018, Sun et al., 2019a], and complex neural models [Dettmers et al., 2018, Nguyen et al., 2018].”
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, unknown): “HyTE [177] takes a time stamp as a hyperplane w τ and projects entity and relation representation as P τ ( h ) = h − w (cid:62) τ h w τ , P τ ( t ) = t − w (cid:62) τ t w τ , and P τ ( r ) = r − w (cid:62) τ r w τ .”
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).”
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks (2020, methodology): “Temporal methods include TTransE (Jiang et al. 2016), HyTE (Dasgupta, Ray, and Talukdar 2018), TA-DistMult (Garc´ıa-Dur´an, Dumancic, and Niepert 2018), Know-Evolve+MLP (Trivedi et al. 2017), DyRep+MLP (Trivedi et al. 2018), R-GCRN+MLP (Seo et al. 2018), and RE-NET (Jin et al. 2019), whereof RE-NET…”
Temporal Graph Networks for Deep Learning on Dynamic Graphs (2020, background): “Other recent works have focused on dynamic knowledge graphs [21, 65, 12, 19].”