research product . program source code . 2019

Negative Sampling for Learning Knowledge Graph Embeddings Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs

Kotnis, Bhushan (Department of Computational Linguistics, Heidelberg University, Germany (2016-2018), NEC Laboratories Europe GmbH (since 2018));
  • Published: 01 Jan 2019
  • Publisher: heiDATA
<p>Reimplementation of four KG factorization methods and six negative sampling methods.</p> <strong> Abstract </strong> </p> Knowledge graphs are large, useful, but incomplete knowledge repositories. They encode knowledge through entities and relations which define each other through the connective structure of the graph. This has inspired methods for the joint embedding of entities and relations in continuous low-dimensional vector spaces, that can be used to induce new edges in the graph, i.e., link prediction in knowledge graphs. Learning these representations relies on contrasting positive instances with negative ones. Knowledge graphs include only positive ...
free text keywords: Arts and Humanities, Computer and Information Science, embedding models, knowledge discovery in knowledge graphs, knowledge graphs, linkprediction, negative sampling, Humanities
Digital Humanities and Cultural Heritage
Download from
program source code . 2019
Provider: B2FIND
Any information missing or wrong?Report an Issue