Matches in SemOpenAlex for { <https://semopenalex.org/work/W3105940150> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W3105940150 abstract "Anomaly detection on attributed network has broad applications in many practical scenarios. Most of existing methods figure out the anomaly detection task by using graph convolution networks to embed the attributed networks. However, these methods will inevitably suffer over-smoothing problems. To approach this problem, in this paper, we propose a graph attention-based autoencoder model. Firstly, we encode the attributed network with a graph attention network. The attention mechanism not only alleviate the over-smoothing problem, but also help encoder learn nodes' representation better. Secondly, we use two decoders to reconstruct the original network and obtain reconstruction errors subsequently. Thus, we are able to detect anomalies by measuring the reconstruction errors. Experiments on real-word datasets show that our proposed model has better performance than other baseline methods in the area under a receiver operating characteristic curve (AUC)." @default.
- W3105940150 created "2020-11-23" @default.
- W3105940150 creator A5023908474 @default.
- W3105940150 creator A5048486573 @default.
- W3105940150 creator A5065058975 @default.
- W3105940150 creator A5085791658 @default.
- W3105940150 date "2020-08-09" @default.
- W3105940150 modified "2023-09-26" @default.
- W3105940150 title "GATAE: Graph Attention-based Anomaly Detection on Attributed Networks" @default.
- W3105940150 cites W2062769337 @default.
- W3105940150 cites W2089554624 @default.
- W3105940150 cites W2112429379 @default.
- W3105940150 cites W2296719434 @default.
- W3105940150 cites W2591281206 @default.
- W3105940150 cites W2621614835 @default.
- W3105940150 cites W2743138268 @default.
- W3105940150 cites W2808544127 @default.
- W3105940150 cites W2808771744 @default.
- W3105940150 cites W2944250323 @default.
- W3105940150 cites W2949435814 @default.
- W3105940150 cites W2963893312 @default.
- W3105940150 cites W2983576094 @default.
- W3105940150 cites W2991132836 @default.
- W3105940150 cites W3011995057 @default.
- W3105940150 cites W4254182148 @default.
- W3105940150 doi "https://doi.org/10.1109/iccc49849.2020.9238879" @default.
- W3105940150 hasPublicationYear "2020" @default.
- W3105940150 type Work @default.
- W3105940150 sameAs 3105940150 @default.
- W3105940150 citedByCount "2" @default.
- W3105940150 countsByYear W31059401502021 @default.
- W3105940150 countsByYear W31059401502022 @default.
- W3105940150 crossrefType "proceedings-article" @default.
- W3105940150 hasAuthorship W3105940150A5023908474 @default.
- W3105940150 hasAuthorship W3105940150A5048486573 @default.
- W3105940150 hasAuthorship W3105940150A5065058975 @default.
- W3105940150 hasAuthorship W3105940150A5085791658 @default.
- W3105940150 hasConcept C154945302 @default.
- W3105940150 hasConcept C41008148 @default.
- W3105940150 hasConcept C739882 @default.
- W3105940150 hasConceptScore W3105940150C154945302 @default.
- W3105940150 hasConceptScore W3105940150C41008148 @default.
- W3105940150 hasConceptScore W3105940150C739882 @default.
- W3105940150 hasFunder F4320321001 @default.
- W3105940150 hasLocation W31059401501 @default.
- W3105940150 hasOpenAccess W3105940150 @default.
- W3105940150 hasPrimaryLocation W31059401501 @default.
- W3105940150 hasRelatedWork W1981470744 @default.
- W3105940150 hasRelatedWork W2136041290 @default.
- W3105940150 hasRelatedWork W2460485004 @default.
- W3105940150 hasRelatedWork W2767431350 @default.
- W3105940150 hasRelatedWork W2769077153 @default.
- W3105940150 hasRelatedWork W2899473595 @default.
- W3105940150 hasRelatedWork W4205473431 @default.
- W3105940150 hasRelatedWork W4285209492 @default.
- W3105940150 hasRelatedWork W4322762270 @default.
- W3105940150 hasRelatedWork W4366150177 @default.
- W3105940150 isParatext "false" @default.
- W3105940150 isRetracted "false" @default.
- W3105940150 magId "3105940150" @default.
- W3105940150 workType "article" @default.