Deriving Validity Time in Knowledge Graph

By Julien Leblay, M. Chekol. 2018

528 citations recorded by the source corpus.

Knowledge Graphs (KGs) are a popular means to represent knowledge on the Web, typically in the form of node/edge labelled directed graphs. We consider temporal KGs, in which edges are further annotated with time intervals, reflecting when the relationship between entities held in time. In this paper, we focus on the task of predicting time validity for unannotated edges. We introduce the problem as a variation of relational embedding. We adapt existing approaches, and explore the importance example selection and the incorporation of side information in the learning process. We present our experimental evaluation in details.

How researchers see this paper

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

1. Woojeong Jin
2. Seyed Mehran Kazemi
3. Rishab Goel
4. Xiang Ren
5. Kshitij Jain
6. Meng Qu
7. Zixuan Li
8. Xisen Jin

Citations in the corpus

• Recurrent Event Network for Reasoning over Temporal Knowledge Graphs (2019, methodology): “The second group of graphs includes WIKI [13] and YAGO [15].”
• Representation Learning for Dynamic Graphs: A Survey (2019, methodology): “Leblay and Chekol (2018) provide other extensions of TransE as well.”
• Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, methodology): “Wikidata: Leblay and Chekol [133] created a temporal knowledge base 17 using Wikidata.”
• Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning (2021, methodology): “There are six typical TKGs commonly used in previous works, namely, ICEWS18 [16], ICEWS14 [9], ICEWS0515 [9], WIKI [21], YAGO [24] and GDELT [22].”
• HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding (2018, background): “KGs have been found to be useful for a variety of tasks, viz., Information Retrieval (Kotov and Zhai, 2012; Xiong and Callan, 2015), Question Answering (Dong et al., 2015; Bordes et al., 2015; Yao and Durme, 2014), among others.”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, unknown): “Leblay and Chekol [175] investigated temporal scope prediction over time-annotated triple, and simply extended existing embedding methods, for example, TransE with the vector-based TTransE defined as Ma et al. [176] also generalized existing static embedding methods and proposed ConT by replacing the”
• Learning Sequence Encoders for Temporal Knowledge Graph Completion (2018, methodology): “We also experimented with the temporal facts from the WIKIDATA data set4 extracted in (Leblay and Chekol, 2018).”
• Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs (2019, methodology): “…the associate into a low dimensional space such as relation embeddings with RNN on the text of time (Garc´ıa-Dur´an et al., 2018), time embeddings (Leblay and Chekol, 2018), temporal hyperplanes (Leblay and Chekol, 2018), diachronic entity embedding (Goel et al., 2020), and tensor decomposition…”