{"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/semantic-preserving-embeddings-for","title":"Semantic Preserving Embeddings for Generalized Graphs","arxiv_id":"1709.02759","date":"2017-09-07","proceeding":null,"authors":["Pedro Almagro-Blanco","Fernando Sancho-Caparrini"],"abstract":"A new approach to the study of Generalized Graphs as semantic data structures\nusing machine learning techniques is presented. We show how vector\nrepresentations maintaining semantic characteristics of the original data can\nbe obtained from a given graph using neural encoding architectures and\nconsidering the topological properties of the graph. Semantic features of these\nnew representations are tested by using some machine learning tasks and new\ndirections on efficient link discovery, entitity retrieval and long distance\nquery methodologies on large relational datasets are investigated using real\ndatasets.\n  ----\n  En este trabajo se presenta un nuevo enfoque en el contexto del aprendizaje\nautom\\'atico multi-relacional para el estudio de Grafos Generalizados. Se\nmuestra c\\'omo se pueden obtener representaciones vectoriales que mantienen\ncaracter\\'isticas sem\\'anticas del grafo original utilizando codificadores\nneuronales y considerando las propiedades topol\\'ogicas del grafo. Adem\\'as, se\neval\\'uan las caracter\\'isticas sem\\'anticas capturadas por estas nuevas\nrepresentaciones y se investigan nuevas metodolog\\'ias eficientes relacionadas\ncon Link Discovery, Entity Retrieval y consultas a larga distancia en grandes\nconjuntos de datos relacionales haciendo uso de bases de datos reales.","url_abs":"http://arxiv.org/abs/1709.02759v1","url_pdf":"http://arxiv.org/pdf/1709.02759v1.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":"semantic-preserving-embeddings-for","repo_url":"https://github.com/palmagro/gg2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"entity-retrieval","task_name":"Entity Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}