Pular para o conteúdo principal

Postagens

Acompanhamento semanal - Checkpoint II

09/09/2021 a 22/09/2021 09/09 - Aula DL (tarde), Aula BD Não Convencional (noite), Revisão vídeos aulas BD Search 10/09 - WTDBD, Lattes2WD 11/09 - WTDBD, Artigo KwS-RDF, Reunião Sérgio (docência) 12/09 - WTDBD, Artigo KwS-RDF, Aula sobre SPARQL (planejamento) 13/09 - Aula BD tool, Material SPARQL CCE 14/09 - Lattes2WD, WTDBD 15/09 - Aula BD Search (tarde), Material SPARQL CCE, Aula SPARQL CCE 15/09 , às 15h 00min - Corpus para o Domínio Acadêmico: Modelos e Aplicações   16/09 - Exercício SPARQL CCE, Aula BD Não Convencional (noite) 17/09 - Tensor Flow Similarity,  Aulas de DL no Youtube (LNCC) 18/09 - Aulas de DL no Youtube (LNCC), Texto DEMO-SBBD, Graph Representation Learning Book 19/09 - xxx 20/09 - Aula SPARQL CCE (noite) 21/09 - xxxxx 22/09 - Reunião BioBD (noite) Continuar Graph Representation Learning Book - cap 5 Livro DL+Search capítulo 4 28/09 - Vídeo para o WTDBD

Graph Representation Learning - Cap 4 - Multi-relational Data and Knowledge Graphs

Fonte: https://www.cs.mcgill.ca/~wlh/grl_book/files/GRL_Book-Chapter_4-Knowledge_Graphs.pdf @article{ author={Hamilton, William L.}, title={Graph Representation Learning}, journal={Synthesis Lectures on Artificial Intelligence and Machine Learning}, volume={14}, number={3}, pages={1-159}, publisher={Morgan and Claypool} }   shallow embedding approaches, where we learn a unique embedding for each node   knowledge graph completion: we are given a multi-relational graph G = ( V , E ), where the edges are defined as tuples e = ( u, ri , v ) indicating the presence of a particular relation ri holding between two nodes. Such multi-relational graphs are often referred to as knowledge graphs , since we can interpret the tuple ( u, ri , v ) as specifying that a particular “fact” holds between the two nodes u and v .     now we have to deal with the presence of multiple di ff erent types of edges. To address this complication, we augment our decoder ...