Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287126985> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4287126985 abstract "Dynamic graph representation learning is a task to learn node embeddings over dynamic networks, and has many important applications, including knowledge graphs, citation networks to social networks. Graphs of this type are usually large-scale but only a small subset of vertices are related in downstream tasks. Current methods are too expensive to this setting as the complexity is at best linear-dependent on both the number of nodes and edges. In this paper, we propose a new method, namely Dynamic Personalized PageRank Embedding (textsc{DynamicPPE}) for learning a target subset of node representations over large-scale dynamic networks. Based on recent advances in local node embedding and a novel computation of dynamic personalized PageRank vector (PPV), textsc{DynamicPPE} has two key ingredients: 1) the per-PPV complexity is $mathcal{O}(m bar{d} / epsilon)$ where $m,bar{d}$, and $epsilon$ are the number of edges received, average degree, global precision error respectively. Thus, the per-edge event update of a single node is only dependent on $bar{d}$ in average; and 2) by using these high quality PPVs and hash kernels, the learned embeddings have properties of both locality and global consistency. These two make it possible to capture the evolution of graph structure effectively. Experimental results demonstrate both the effectiveness and efficiency of the proposed method over large-scale dynamic networks. We apply textsc{DynamicPPE} to capture the embedding change of Chinese cities in the Wikipedia graph during this ongoing COVID-19 pandemic (https://en.wikipedia.org/wiki/COVID-19_pandemic). Our results show that these representations successfully encode the dynamics of the Wikipedia graph." @default.
- W4287126985 created "2022-07-25" @default.
- W4287126985 creator A5025263659 @default.
- W4287126985 creator A5037714721 @default.
- W4287126985 creator A5060741187 @default.
- W4287126985 date "2021-06-02" @default.
- W4287126985 modified "2023-10-16" @default.
- W4287126985 title "Subset Node Representation Learning over Large Dynamic Graphs" @default.
- W4287126985 hasPublicationYear "2021" @default.
- W4287126985 type Work @default.
- W4287126985 citedByCount "0" @default.
- W4287126985 crossrefType "posted-content" @default.
- W4287126985 hasAuthorship W4287126985A5025263659 @default.
- W4287126985 hasAuthorship W4287126985A5037714721 @default.
- W4287126985 hasAuthorship W4287126985A5060741187 @default.
- W4287126985 hasBestOaLocation W42871269851 @default.
- W4287126985 hasConcept C121332964 @default.
- W4287126985 hasConcept C127413603 @default.
- W4287126985 hasConcept C132525143 @default.
- W4287126985 hasConcept C138885662 @default.
- W4287126985 hasConcept C154945302 @default.
- W4287126985 hasConcept C24890656 @default.
- W4287126985 hasConcept C2775997480 @default.
- W4287126985 hasConcept C2779172887 @default.
- W4287126985 hasConcept C2779808786 @default.
- W4287126985 hasConcept C38652104 @default.
- W4287126985 hasConcept C41008148 @default.
- W4287126985 hasConcept C41608201 @default.
- W4287126985 hasConcept C41895202 @default.
- W4287126985 hasConcept C59404180 @default.
- W4287126985 hasConcept C62611344 @default.
- W4287126985 hasConcept C66938386 @default.
- W4287126985 hasConcept C80444323 @default.
- W4287126985 hasConcept C99138194 @default.
- W4287126985 hasConceptScore W4287126985C121332964 @default.
- W4287126985 hasConceptScore W4287126985C127413603 @default.
- W4287126985 hasConceptScore W4287126985C132525143 @default.
- W4287126985 hasConceptScore W4287126985C138885662 @default.
- W4287126985 hasConceptScore W4287126985C154945302 @default.
- W4287126985 hasConceptScore W4287126985C24890656 @default.
- W4287126985 hasConceptScore W4287126985C2775997480 @default.
- W4287126985 hasConceptScore W4287126985C2779172887 @default.
- W4287126985 hasConceptScore W4287126985C2779808786 @default.
- W4287126985 hasConceptScore W4287126985C38652104 @default.
- W4287126985 hasConceptScore W4287126985C41008148 @default.
- W4287126985 hasConceptScore W4287126985C41608201 @default.
- W4287126985 hasConceptScore W4287126985C41895202 @default.
- W4287126985 hasConceptScore W4287126985C59404180 @default.
- W4287126985 hasConceptScore W4287126985C62611344 @default.
- W4287126985 hasConceptScore W4287126985C66938386 @default.
- W4287126985 hasConceptScore W4287126985C80444323 @default.
- W4287126985 hasConceptScore W4287126985C99138194 @default.
- W4287126985 hasLocation W42871269851 @default.
- W4287126985 hasOpenAccess W4287126985 @default.
- W4287126985 hasPrimaryLocation W42871269851 @default.
- W4287126985 hasRelatedWork W10324078 @default.
- W4287126985 hasRelatedWork W11577049 @default.
- W4287126985 hasRelatedWork W12580684 @default.
- W4287126985 hasRelatedWork W13224608 @default.
- W4287126985 hasRelatedWork W14500723 @default.
- W4287126985 hasRelatedWork W1480935 @default.
- W4287126985 hasRelatedWork W1586417 @default.
- W4287126985 hasRelatedWork W6790349 @default.
- W4287126985 hasRelatedWork W7585623 @default.
- W4287126985 hasRelatedWork W8951285 @default.
- W4287126985 isParatext "false" @default.
- W4287126985 isRetracted "false" @default.
- W4287126985 workType "article" @default.