{"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/proje-embedding-projection-for-knowledge","title":"ProjE: Embedding Projection for Knowledge Graph Completion","arxiv_id":"1611.05425","date":"2016-11-16","proceeding":null,"authors":["Baoxu Shi","Tim Weninger"],"abstract":"With the large volume of new information created every day, determining the\nvalidity of information in a knowledge graph and filling in its missing parts\nare crucial tasks for many researchers and practitioners. To address this\nchallenge, a number of knowledge graph completion methods have been developed\nusing low-dimensional graph embeddings. Although researchers continue to\nimprove these models using an increasingly complex feature space, we show that\nsimple changes in the architecture of the underlying model can outperform\nstate-of-the-art models without the need for complex feature engineering. In\nthis work, we present a shared variable neural network model called ProjE that\nfills-in missing information in a knowledge graph by learning joint embeddings\nof the knowledge graph's entities and edges, and through subtle, but important,\nchanges to the standard loss function. In doing so, ProjE has a parameter size\nthat is smaller than 11 out of 15 existing methods while performing $37\\%$\nbetter than the current-best method on standard datasets. We also show, via a\nnew fact checking task, that ProjE is capable of accurately determining the\nveracity of many declarative statements.","url_abs":"http://arxiv.org/abs/1611.05425v1","url_pdf":"http://arxiv.org/pdf/1611.05425v1.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":"proje-embedding-projection-for-knowledge","repo_url":"https://github.com/Sujit-O/pykg2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"proje-embedding-projection-for-knowledge","repo_url":"https://github.com/sheepover96/ProjE.torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"knowledge-graph-completion","task_name":"Knowledge Graph Completion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.05425","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}