{"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-base-completion-baseline-strikes","title":"Knowledge Base Completion: Baseline strikes back (Again)","arxiv_id":"2005.00804","date":"2020-05-02","proceeding":null,"authors":["Prachi Jain","Sushant Rathi","Mausam","Soumen Chakrabarti"],"abstract":"Knowledge Base Completion (KBC) has been a very active area lately. Several recent KBCpapers propose architectural changes, new training methods, or even new formulations. KBC systems are usually evaluated on standard benchmark datasets: FB15k, FB15k-237, WN18, WN18RR, and Yago3-10. Most existing methods train with a small number of negative samples for each positive instance in these datasets to save computational costs. This paper discusses how recent developments allow us to use all available negative samples for training. We show that Complex, when trained using all available negative samples, gives near state-of-the-art performance on all the datasets. We call this approach COMPLEX-V2. We also highlight how various multiplicative KBC methods, recently proposed in the literature, benefit from this train-ing regime and become indistinguishable in terms of performance on most datasets. Our work calls for a reassessment of their individual value, in light of these findings.","url_abs":"https://arxiv.org/abs/2005.00804v3","url_pdf":"https://arxiv.org/pdf/2005.00804v3.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-base-completion-baseline-strikes","repo_url":"https://github.com/dair-iitd/kbc-baseline","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"knowledge-base-completion","task_name":"Knowledge Base Completion"},{"task_slug":"knowledge-base-population","task_name":"Knowledge Base Population"},{"task_slug":"knowledge-graph-completion","task_name":"Knowledge Graph Completion"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.00804","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}