{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/knowledge-graph-fact-prediction-via-knowledge","title":"Knowledge Graph Fact Prediction via Knowledge-Enriched Tensor Factorization","arxiv_id":"1902.03077","date":"2019-02-08","proceeding":"Journal of Web Semantics 2019 12","authors":["Ankur Padia","Kostantinos Kalpakis","Francis Ferraro","Tim Finin"],"abstract":"We present a family of novel methods for embedding knowledge graphs into\nreal-valued tensors. These tensor-based embeddings capture the ordered\nrelations that are typical in the knowledge graphs represented by semantic web\nlanguages like RDF. Unlike many previous models, our methods can easily use\nprior background knowledge provided by users or extracted automatically from\nexisting knowledge graphs. In addition to providing more robust methods for\nknowledge graph embedding, we provide a provably-convergent, linear tensor\nfactorization algorithm. We demonstrate the efficacy of our models for the task\nof predicting new facts across eight different knowledge graphs, achieving\nbetween 5% and 50% relative improvement over existing state-of-the-art\nknowledge graph embedding techniques. Our empirical evaluation shows that all\nof the tensor decomposition models perform well when the average degree of an\nentity in a graph is high, with constraint-based models doing better on graphs\nwith a small number of highly similar relations and regularization-based models\ndominating for graphs with relations of varying degrees of similarity.","url_abs":"http://arxiv.org/abs/1902.03077v1","url_pdf":"http://arxiv.org/pdf/1902.03077v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"knowledge-graph-fact-prediction-via-knowledge","repo_url":"https://github.com/Ebiquity/KGFP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"tensor-decomposition","task_name":"Tensor Decomposition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.03077","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}