{"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-embedding-with-3d-compound","title":"Knowledge Graph Embedding with 3D Compound Geometric Transformations","arxiv_id":"2304.00378","date":"2023-04-01","proceeding":null,"authors":["Xiou Ge","Yun-Cheng Wang","Bin Wang","C. -C. Jay Kuo"],"abstract":"The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was proposed as a new KGE model, Rotate3D, by leveraging its non-commutative property. Inspired by CompoundE and Rotate3D, we leverage 3D compound geometric transformations, including translation, rotation, scaling, reflection, and shear and propose a family of KGE models, named CompoundE3D, in this work. CompoundE3D allows multiple design variants to match rich underlying characteristics of a KG. Since each variant has its own advantages on a subset of relations, an ensemble of multiple variants can yield superior performance. The effectiveness and flexibility of CompoundE3D are experimentally verified on four popular link prediction datasets.","url_abs":"https://arxiv.org/abs/2304.00378v1","url_pdf":"https://arxiv.org/pdf/2304.00378v1.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-embedding-with-3d-compound","repo_url":"https://github.com/hughxiouge/CompoundE3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-property-prediction-on-ogbl-wikikg2","task":"Link Property Prediction","dataset":"ogbl-wikikg2","model":"CompoundE3D","rank_in_archive_order":7,"of":30,"metrics":{"Ext. data":"No","Number of params":"750662700","Test MRR":"0.7006 ± 0.0011","Validation MRR":"0.7175 ± 0.0015"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.00378","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}