Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294785738> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4294785738 abstract "Temporal networks have been widely used to model real-world complex systems such as financial systems and e-commerce systems. In a temporal network, the joint neighborhood of a set of nodes often provides crucial structural information useful for predicting whether they may interact at a certain time. However, recent representation learning methods for temporal networks often fail to extract such information or depend on online construction of structural features, which is time-consuming. To address the issue, this work proposes Neighborhood-Aware Temporal network model (NAT). For each node in the network, NAT abandons the commonly-used one-single-vector-based representation while adopting a novel dictionary-type neighborhood representation. Such a dictionary representation records a downsampled set of the neighboring nodes as keys, and allows fast construction of structural features for a joint neighborhood of multiple nodes. We also design a dedicated data structure termed N-cache to support parallel access and update of those dictionary representations on GPUs. NAT gets evaluated over seven real-world large-scale temporal networks. NAT not only outperforms all cutting-edge baselines by averaged 1.2% and 4.2% in transductive and inductive link prediction accuracy, respectively, but also keeps scalable by achieving a speed-up of 4.1-76.7x against the baselines that adopt joint structural features and achieves a speed-up of 1.6-4.0x against the baselines that cannot adopt those features. The link to the code: https: //github.com/Graph-COM/Neighborhood-Aware-Temporal-Network." @default.
- W4294785738 created "2022-09-06" @default.
- W4294785738 creator A5065370043 @default.
- W4294785738 creator A5086290413 @default.
- W4294785738 date "2022-09-02" @default.
- W4294785738 modified "2023-10-16" @default.
- W4294785738 title "Neighborhood-aware Scalable Temporal Network Representation Learning" @default.
- W4294785738 doi "https://doi.org/10.48550/arxiv.2209.01084" @default.
- W4294785738 hasPublicationYear "2022" @default.
- W4294785738 type Work @default.
- W4294785738 citedByCount "0" @default.
- W4294785738 crossrefType "posted-content" @default.
- W4294785738 hasAuthorship W4294785738A5065370043 @default.
- W4294785738 hasAuthorship W4294785738A5086290413 @default.
- W4294785738 hasBestOaLocation W42947857381 @default.
- W4294785738 hasConcept C124101348 @default.
- W4294785738 hasConcept C127413603 @default.
- W4294785738 hasConcept C132525143 @default.
- W4294785738 hasConcept C154945302 @default.
- W4294785738 hasConcept C162307627 @default.
- W4294785738 hasConcept C177264268 @default.
- W4294785738 hasConcept C17744445 @default.
- W4294785738 hasConcept C199360897 @default.
- W4294785738 hasConcept C199539241 @default.
- W4294785738 hasConcept C2776359362 @default.
- W4294785738 hasConcept C2776760102 @default.
- W4294785738 hasConcept C41008148 @default.
- W4294785738 hasConcept C48044578 @default.
- W4294785738 hasConcept C59404180 @default.
- W4294785738 hasConcept C62611344 @default.
- W4294785738 hasConcept C66938386 @default.
- W4294785738 hasConcept C77088390 @default.
- W4294785738 hasConcept C80444323 @default.
- W4294785738 hasConcept C94625758 @default.
- W4294785738 hasConceptScore W4294785738C124101348 @default.
- W4294785738 hasConceptScore W4294785738C127413603 @default.
- W4294785738 hasConceptScore W4294785738C132525143 @default.
- W4294785738 hasConceptScore W4294785738C154945302 @default.
- W4294785738 hasConceptScore W4294785738C162307627 @default.
- W4294785738 hasConceptScore W4294785738C177264268 @default.
- W4294785738 hasConceptScore W4294785738C17744445 @default.
- W4294785738 hasConceptScore W4294785738C199360897 @default.
- W4294785738 hasConceptScore W4294785738C199539241 @default.
- W4294785738 hasConceptScore W4294785738C2776359362 @default.
- W4294785738 hasConceptScore W4294785738C2776760102 @default.
- W4294785738 hasConceptScore W4294785738C41008148 @default.
- W4294785738 hasConceptScore W4294785738C48044578 @default.
- W4294785738 hasConceptScore W4294785738C59404180 @default.
- W4294785738 hasConceptScore W4294785738C62611344 @default.
- W4294785738 hasConceptScore W4294785738C66938386 @default.
- W4294785738 hasConceptScore W4294785738C77088390 @default.
- W4294785738 hasConceptScore W4294785738C80444323 @default.
- W4294785738 hasConceptScore W4294785738C94625758 @default.
- W4294785738 hasLocation W42947857381 @default.
- W4294785738 hasLocation W42947857382 @default.
- W4294785738 hasOpenAccess W4294785738 @default.
- W4294785738 hasPrimaryLocation W42947857381 @default.
- W4294785738 hasRelatedWork W2068266569 @default.
- W4294785738 hasRelatedWork W2166829200 @default.
- W4294785738 hasRelatedWork W2405379563 @default.
- W4294785738 hasRelatedWork W2804057010 @default.
- W4294785738 hasRelatedWork W2965265899 @default.
- W4294785738 hasRelatedWork W2989955213 @default.
- W4294785738 hasRelatedWork W3118281188 @default.
- W4294785738 hasRelatedWork W3127111063 @default.
- W4294785738 hasRelatedWork W4287391817 @default.
- W4294785738 hasRelatedWork W4367684998 @default.
- W4294785738 isParatext "false" @default.
- W4294785738 isRetracted "false" @default.
- W4294785738 workType "article" @default.