Matches in SemOpenAlex for { <https://semopenalex.org/work/W3175013358> ?p ?o ?g. }
- W3175013358 abstract "Networks found in the real-world are numerous and varied. A common type of network is the heterogeneous network, where the nodes (and edges) can be of different types. Accordingly, there have been efforts at learning representations of these heterogeneous networks in low-dimensional space. However, most of the existing heterogeneous network embedding methods suffer from the following two drawbacks: (1) The target space is usually Euclidean. Conversely, many recent works have shown that complex networks may have hyperbolic latent anatomy, which is non-Euclidean. (2) These methods usually rely on meta-paths, which require domain-specific prior knowledge for meta-path selection. Additionally, different down-streaming tasks on the same network might require different meta-paths in order to generate task-specific embeddings. In this paper, we propose a novel self-guided random walk method that does not require meta-path for embedding heterogeneous networks into hyperbolic space. We conduct thorough experiments for the tasks of network reconstruction and link prediction on two public datasets, showing that our model outperforms a variety of well-known baselines across all tasks." @default.
- W3175013358 created "2021-07-05" @default.
- W3175013358 creator A5023339675 @default.
- W3175013358 creator A5023492006 @default.
- W3175013358 creator A5035399743 @default.
- W3175013358 creator A5043402333 @default.
- W3175013358 creator A5068349442 @default.
- W3175013358 creator A5072940415 @default.
- W3175013358 date "2021-06-18" @default.
- W3175013358 modified "2023-09-25" @default.
- W3175013358 title "Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path" @default.
- W3175013358 cites W1533230146 @default.
- W3175013358 cites W2090891622 @default.
- W3175013358 cites W2127795553 @default.
- W3175013358 cites W2130789338 @default.
- W3175013358 cites W2153579005 @default.
- W3175013358 cites W2176446742 @default.
- W3175013358 cites W2199357291 @default.
- W3175013358 cites W2283196293 @default.
- W3175013358 cites W2387462954 @default.
- W3175013358 cites W2393319904 @default.
- W3175013358 cites W2604314403 @default.
- W3175013358 cites W2605234117 @default.
- W3175013358 cites W2743104969 @default.
- W3175013358 cites W2767774008 @default.
- W3175013358 cites W2796314760 @default.
- W3175013358 cites W2803760543 @default.
- W3175013358 cites W2809435521 @default.
- W3175013358 cites W2885826990 @default.
- W3175013358 cites W2896161497 @default.
- W3175013358 cites W2904510605 @default.
- W3175013358 cites W2909137510 @default.
- W3175013358 cites W2911286998 @default.
- W3175013358 cites W2922036394 @default.
- W3175013358 cites W2950393809 @default.
- W3175013358 cites W2962756421 @default.
- W3175013358 cites W2962936818 @default.
- W3175013358 cites W2963844113 @default.
- W3175013358 cites W2965857891 @default.
- W3175013358 cites W2984834462 @default.
- W3175013358 cites W3012871709 @default.
- W3175013358 cites W3096399240 @default.
- W3175013358 cites W3102317997 @default.
- W3175013358 cites W3104097132 @default.
- W3175013358 cites W3104717349 @default.
- W3175013358 cites W3105705953 @default.
- W3175013358 doi "https://doi.org/10.48550/arxiv.2106.09923" @default.
- W3175013358 hasPublicationYear "2021" @default.
- W3175013358 type Work @default.
- W3175013358 sameAs 3175013358 @default.
- W3175013358 citedByCount "0" @default.
- W3175013358 crossrefType "posted-content" @default.
- W3175013358 hasAuthorship W3175013358A5023339675 @default.
- W3175013358 hasAuthorship W3175013358A5023492006 @default.
- W3175013358 hasAuthorship W3175013358A5035399743 @default.
- W3175013358 hasAuthorship W3175013358A5043402333 @default.
- W3175013358 hasAuthorship W3175013358A5068349442 @default.
- W3175013358 hasAuthorship W3175013358A5072940415 @default.
- W3175013358 hasBestOaLocation W31750133581 @default.
- W3175013358 hasConcept C105795698 @default.
- W3175013358 hasConcept C108037233 @default.
- W3175013358 hasConcept C111919701 @default.
- W3175013358 hasConcept C121194460 @default.
- W3175013358 hasConcept C129782007 @default.
- W3175013358 hasConcept C136197465 @default.
- W3175013358 hasConcept C154945302 @default.
- W3175013358 hasConcept C158207573 @default.
- W3175013358 hasConcept C162324750 @default.
- W3175013358 hasConcept C186450821 @default.
- W3175013358 hasConcept C187736073 @default.
- W3175013358 hasConcept C202444582 @default.
- W3175013358 hasConcept C2524010 @default.
- W3175013358 hasConcept C2777735758 @default.
- W3175013358 hasConcept C2778572836 @default.
- W3175013358 hasConcept C2780451532 @default.
- W3175013358 hasConcept C31258907 @default.
- W3175013358 hasConcept C33923547 @default.
- W3175013358 hasConcept C41008148 @default.
- W3175013358 hasConcept C41608201 @default.
- W3175013358 hasConcept C555944384 @default.
- W3175013358 hasConcept C76155785 @default.
- W3175013358 hasConcept C80444323 @default.
- W3175013358 hasConcept C83677898 @default.
- W3175013358 hasConceptScore W3175013358C105795698 @default.
- W3175013358 hasConceptScore W3175013358C108037233 @default.
- W3175013358 hasConceptScore W3175013358C111919701 @default.
- W3175013358 hasConceptScore W3175013358C121194460 @default.
- W3175013358 hasConceptScore W3175013358C129782007 @default.
- W3175013358 hasConceptScore W3175013358C136197465 @default.
- W3175013358 hasConceptScore W3175013358C154945302 @default.
- W3175013358 hasConceptScore W3175013358C158207573 @default.
- W3175013358 hasConceptScore W3175013358C162324750 @default.
- W3175013358 hasConceptScore W3175013358C186450821 @default.
- W3175013358 hasConceptScore W3175013358C187736073 @default.
- W3175013358 hasConceptScore W3175013358C202444582 @default.
- W3175013358 hasConceptScore W3175013358C2524010 @default.
- W3175013358 hasConceptScore W3175013358C2777735758 @default.
- W3175013358 hasConceptScore W3175013358C2778572836 @default.
- W3175013358 hasConceptScore W3175013358C2780451532 @default.
- W3175013358 hasConceptScore W3175013358C31258907 @default.