Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311711472> ?p ?o ?g. }
- W4311711472 endingPage "103399" @default.
- W4311711472 startingPage "103399" @default.
- W4311711472 abstract "Fraud has seriously influenced the social media ecosystems, and malicious users pursue high profit by disseminating fake information. Graph neural networks (GNN) have shown a promising potential for fraud detection tasks, where fraudulent nodes are identified by aggregating the neighbors that share similar feedbacks and relations. However, crafty fraudsters can trivially get around such detection via seemingly legitimate feedbacks once connected to legitimate users. In this paper, we leverage Relational Density Theory and propose a Hierarchical Attention-based Graph Neural Network (HA-GNN) for fraud detection, which incorporates weighted adjacency matrices across different relations against camouflage. This is motivated by the fact that there are dense connections between fraudsters who collectively participate in fraud activities. Specifically, we design a relation attention module to reflect the tie strength between two nodes, while a neighborhood attention module to capture the long-range structural affinity associated with the graph. We generate node embeddings by aggregating information from local/long-range structures and original node features. Experiments on three real-world datasets demonstrate that our approach achieves 3.21 – 9.97% RUC improvement compared with the state-of-the-arts." @default.
- W4311711472 created "2022-12-28" @default.
- W4311711472 creator A5014787907 @default.
- W4311711472 creator A5016507963 @default.
- W4311711472 creator A5060178337 @default.
- W4311711472 date "2023-02-01" @default.
- W4311711472 modified "2023-10-05" @default.
- W4311711472 title "Improving fraud detection via hierarchical attention-based Graph Neural Network" @default.
- W4311711472 cites W113059239 @default.
- W4311711472 cites W1965586806 @default.
- W4311711472 cites W2064058256 @default.
- W4311711472 cites W2136891251 @default.
- W4311711472 cites W2159359879 @default.
- W4311711472 cites W2897862648 @default.
- W4311711472 cites W2903871660 @default.
- W4311711472 cites W2904890881 @default.
- W4311711472 cites W2911286998 @default.
- W4311711472 cites W2945996535 @default.
- W4311711472 cites W2963146368 @default.
- W4311711472 cites W2963415211 @default.
- W4311711472 cites W2984239289 @default.
- W4311711472 cites W2997128522 @default.
- W4311711472 cites W3023756969 @default.
- W4311711472 cites W3035298482 @default.
- W4311711472 cites W3040200962 @default.
- W4311711472 cites W3045200674 @default.
- W4311711472 cites W3068123808 @default.
- W4311711472 cites W3098259638 @default.
- W4311711472 cites W3099825604 @default.
- W4311711472 cites W3100848837 @default.
- W4311711472 cites W3103720336 @default.
- W4311711472 cites W3153858161 @default.
- W4311711472 cites W3156449551 @default.
- W4311711472 cites W3169637772 @default.
- W4311711472 cites W3210137232 @default.
- W4311711472 cites W4210257598 @default.
- W4311711472 cites W845365781 @default.
- W4311711472 doi "https://doi.org/10.1016/j.jisa.2022.103399" @default.
- W4311711472 hasPublicationYear "2023" @default.
- W4311711472 type Work @default.
- W4311711472 citedByCount "1" @default.
- W4311711472 countsByYear W43117114722023 @default.
- W4311711472 crossrefType "journal-article" @default.
- W4311711472 hasAuthorship W4311711472A5014787907 @default.
- W4311711472 hasAuthorship W4311711472A5016507963 @default.
- W4311711472 hasAuthorship W4311711472A5060178337 @default.
- W4311711472 hasBestOaLocation W43117114722 @default.
- W4311711472 hasConcept C101780184 @default.
- W4311711472 hasConcept C110484373 @default.
- W4311711472 hasConcept C11413529 @default.
- W4311711472 hasConcept C124101348 @default.
- W4311711472 hasConcept C132525143 @default.
- W4311711472 hasConcept C136764020 @default.
- W4311711472 hasConcept C153083717 @default.
- W4311711472 hasConcept C154945302 @default.
- W4311711472 hasConcept C180356752 @default.
- W4311711472 hasConcept C2776196576 @default.
- W4311711472 hasConcept C2777522414 @default.
- W4311711472 hasConcept C38652104 @default.
- W4311711472 hasConcept C41008148 @default.
- W4311711472 hasConcept C50644808 @default.
- W4311711472 hasConcept C518677369 @default.
- W4311711472 hasConcept C76155785 @default.
- W4311711472 hasConcept C80444323 @default.
- W4311711472 hasConceptScore W4311711472C101780184 @default.
- W4311711472 hasConceptScore W4311711472C110484373 @default.
- W4311711472 hasConceptScore W4311711472C11413529 @default.
- W4311711472 hasConceptScore W4311711472C124101348 @default.
- W4311711472 hasConceptScore W4311711472C132525143 @default.
- W4311711472 hasConceptScore W4311711472C136764020 @default.
- W4311711472 hasConceptScore W4311711472C153083717 @default.
- W4311711472 hasConceptScore W4311711472C154945302 @default.
- W4311711472 hasConceptScore W4311711472C180356752 @default.
- W4311711472 hasConceptScore W4311711472C2776196576 @default.
- W4311711472 hasConceptScore W4311711472C2777522414 @default.
- W4311711472 hasConceptScore W4311711472C38652104 @default.
- W4311711472 hasConceptScore W4311711472C41008148 @default.
- W4311711472 hasConceptScore W4311711472C50644808 @default.
- W4311711472 hasConceptScore W4311711472C518677369 @default.
- W4311711472 hasConceptScore W4311711472C76155785 @default.
- W4311711472 hasConceptScore W4311711472C80444323 @default.
- W4311711472 hasFunder F4320321001 @default.
- W4311711472 hasFunder F4320322919 @default.
- W4311711472 hasFunder F4320335777 @default.
- W4311711472 hasLocation W43117114721 @default.
- W4311711472 hasLocation W43117114722 @default.
- W4311711472 hasOpenAccess W4311711472 @default.
- W4311711472 hasPrimaryLocation W43117114721 @default.
- W4311711472 hasRelatedWork W1997448565 @default.
- W4311711472 hasRelatedWork W2374780422 @default.
- W4311711472 hasRelatedWork W2604585036 @default.
- W4311711472 hasRelatedWork W3164306936 @default.
- W4311711472 hasRelatedWork W3164688832 @default.
- W4311711472 hasRelatedWork W3194558310 @default.
- W4311711472 hasRelatedWork W3195358311 @default.
- W4311711472 hasRelatedWork W3201002138 @default.
- W4311711472 hasRelatedWork W4226162056 @default.
- W4311711472 hasRelatedWork W4287178724 @default.