Matches in SemOpenAlex for { <https://semopenalex.org/work/W2992765830> ?p ?o ?g. }
- W2992765830 abstract "Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks. However, most existing algorithms ignore the existence of inherent data distribution and even noises. This may significantly increase the phenomenon of over-fitting and deteriorate the testing accuracy. In this paper, we propose a Distribution-induced Bidirectional Generative Adversarial Network (named DBGAN) for graph representation learning. Instead of the widely used normal distribution assumption, the prior distribution of latent representation in our DBGAN is estimated in a structure-aware way, which implicitly bridges the graph and feature spaces by prototype learning. Thus discriminative and robust representations are generated for all nodes. Furthermore, to improve their generalization ability while preserving representation ability, the sample-level and distribution-level consistency is well balanced via a bidirectional adversarial learning framework. An extensive group of experiments are then carefully designed and presented, demonstrating that our DBGAN obtains remarkably more favorable trade-off between representation and robustness, and meanwhile is dimension-efficient, over currently available alternatives in various tasks." @default.
- W2992765830 created "2019-12-13" @default.
- W2992765830 creator A5000727470 @default.
- W2992765830 creator A5017102094 @default.
- W2992765830 creator A5028127027 @default.
- W2992765830 creator A5042419001 @default.
- W2992765830 creator A5078959651 @default.
- W2992765830 creator A5086302674 @default.
- W2992765830 date "2019-12-04" @default.
- W2992765830 modified "2023-09-26" @default.
- W2992765830 title "Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning" @default.
- W2992765830 cites W1522301498 @default.
- W2992765830 cites W1908728294 @default.
- W2992765830 cites W2090891622 @default.
- W2992765830 cites W2099471712 @default.
- W2992765830 cites W2123549998 @default.
- W2992765830 cites W2139694940 @default.
- W2992765830 cites W2150593711 @default.
- W2992765830 cites W2153959628 @default.
- W2992765830 cites W2155461593 @default.
- W2992765830 cites W2165874743 @default.
- W2992765830 cites W2168627253 @default.
- W2992765830 cites W2187089797 @default.
- W2992765830 cites W2187580259 @default.
- W2992765830 cites W2242161203 @default.
- W2992765830 cites W2387462954 @default.
- W2992765830 cites W2393319904 @default.
- W2992765830 cites W2411541852 @default.
- W2992765830 cites W2412320034 @default.
- W2992765830 cites W2415243320 @default.
- W2992765830 cites W2519887557 @default.
- W2992765830 cites W2554952599 @default.
- W2992765830 cites W2604942799 @default.
- W2992765830 cites W2739748921 @default.
- W2992765830 cites W2767404761 @default.
- W2992765830 cites W2808987817 @default.
- W2992765830 cites W2893944917 @default.
- W2992765830 cites W2950352474 @default.
- W2992765830 cites W2950905235 @default.
- W2992765830 cites W2951451004 @default.
- W2992765830 cites W2962756421 @default.
- W2992765830 cites W2962879692 @default.
- W2992765830 cites W2962904108 @default.
- W2992765830 cites W2963169753 @default.
- W2992765830 cites W2970241862 @default.
- W2992765830 cites W2981450816 @default.
- W2992765830 cites W3103995645 @default.
- W2992765830 cites W3104038788 @default.
- W2992765830 cites W3104097132 @default.
- W2992765830 cites W67413104 @default.
- W2992765830 doi "https://doi.org/10.48550/arxiv.1912.01899" @default.
- W2992765830 hasPublicationYear "2019" @default.
- W2992765830 type Work @default.
- W2992765830 sameAs 2992765830 @default.
- W2992765830 citedByCount "0" @default.
- W2992765830 crossrefType "posted-content" @default.
- W2992765830 hasAuthorship W2992765830A5000727470 @default.
- W2992765830 hasAuthorship W2992765830A5017102094 @default.
- W2992765830 hasAuthorship W2992765830A5028127027 @default.
- W2992765830 hasAuthorship W2992765830A5042419001 @default.
- W2992765830 hasAuthorship W2992765830A5078959651 @default.
- W2992765830 hasAuthorship W2992765830A5086302674 @default.
- W2992765830 hasBestOaLocation W29927658301 @default.
- W2992765830 hasConcept C104317684 @default.
- W2992765830 hasConcept C119857082 @default.
- W2992765830 hasConcept C132525143 @default.
- W2992765830 hasConcept C154945302 @default.
- W2992765830 hasConcept C167966045 @default.
- W2992765830 hasConcept C17744445 @default.
- W2992765830 hasConcept C185592680 @default.
- W2992765830 hasConcept C199539241 @default.
- W2992765830 hasConcept C2776359362 @default.
- W2992765830 hasConcept C2776436953 @default.
- W2992765830 hasConcept C37736160 @default.
- W2992765830 hasConcept C39890363 @default.
- W2992765830 hasConcept C41008148 @default.
- W2992765830 hasConcept C55493867 @default.
- W2992765830 hasConcept C59404180 @default.
- W2992765830 hasConcept C63479239 @default.
- W2992765830 hasConcept C66746571 @default.
- W2992765830 hasConcept C80444323 @default.
- W2992765830 hasConcept C94625758 @default.
- W2992765830 hasConcept C97931131 @default.
- W2992765830 hasConceptScore W2992765830C104317684 @default.
- W2992765830 hasConceptScore W2992765830C119857082 @default.
- W2992765830 hasConceptScore W2992765830C132525143 @default.
- W2992765830 hasConceptScore W2992765830C154945302 @default.
- W2992765830 hasConceptScore W2992765830C167966045 @default.
- W2992765830 hasConceptScore W2992765830C17744445 @default.
- W2992765830 hasConceptScore W2992765830C185592680 @default.
- W2992765830 hasConceptScore W2992765830C199539241 @default.
- W2992765830 hasConceptScore W2992765830C2776359362 @default.
- W2992765830 hasConceptScore W2992765830C2776436953 @default.
- W2992765830 hasConceptScore W2992765830C37736160 @default.
- W2992765830 hasConceptScore W2992765830C39890363 @default.
- W2992765830 hasConceptScore W2992765830C41008148 @default.
- W2992765830 hasConceptScore W2992765830C55493867 @default.
- W2992765830 hasConceptScore W2992765830C59404180 @default.
- W2992765830 hasConceptScore W2992765830C63479239 @default.
- W2992765830 hasConceptScore W2992765830C66746571 @default.