{"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/embedding-uncertain-knowledge-graphs","title":"Embedding Uncertain Knowledge Graphs","arxiv_id":"1811.10667","date":"2018-11-26","proceeding":null,"authors":["Xuelu Chen","Muhao Chen","Weijia Shi","Yizhou Sun","Carlo Zaniolo"],"abstract":"Embedding models for deterministic Knowledge Graphs (KG) have been\nextensively studied, with the purpose of capturing latent semantic relations\nbetween entities and incorporating the structured knowledge into machine\nlearning. However, there are many KGs that model uncertain knowledge, which\ntypically model the inherent uncertainty of relations facts with a confidence\nscore, and embedding such uncertain knowledge represents an unresolved\nchallenge. The capturing of uncertain knowledge will benefit many\nknowledge-driven applications such as question answering and semantic search by\nproviding more natural characterization of the knowledge. In this paper, we\npropose a novel uncertain KG embedding model UKGE, which aims to preserve both\nstructural and uncertainty information of relation facts in the embedding\nspace. Unlike previous models that characterize relation facts with binary\nclassification techniques, UKGE learns embeddings according to the confidence\nscores of uncertain relation facts. To further enhance the precision of UKGE,\nwe also introduce probabilistic soft logic to infer confidence scores for\nunseen relation facts during training. We propose and evaluate two variants of\nUKGE based on different learning objectives. Experiments are conducted on three\nreal-world uncertain KGs via three tasks, i.e. confidence prediction, relation\nfact ranking, and relation fact classification. UKGE shows effectiveness in\ncapturing uncertain knowledge by achieving promising results on these tasks,\nand consistently outperforms baselines on these tasks.","url_abs":"http://arxiv.org/abs/1811.10667v2","url_pdf":"http://arxiv.org/pdf/1811.10667v2.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":"embedding-uncertain-knowledge-graphs","repo_url":"https://github.com/stasl0217/UKGE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"Relation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10667","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}