Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386965067> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4386965067 endingPage "121643" @default.
- W4386965067 startingPage "121643" @default.
- W4386965067 abstract "Graph neural networks (GNNs) have exhibited remarkable success in fraud detection. However, detecting fraud in datasets with scattered graphic densities and multiple relations remains challenging. This is a prevalent issue in fraud detection as fraudsters often employ diverse relationship types to camouflage their activities. Moreover, the constrained interconnectivity between nodes contributes to a scarcity of informative data, thereby intensifying the influence of raw features and further compounding the difficulties in fraud detection processes. To address these challenges, we present SCN_GNN (Strongly Connected Nodes-Graph Neural Network), a novel algorithm for fraud detection, that proposes two node sampling strategies based on the fusion of strong node information and graph topology information. Among them, the structured similarity-aware module (SSAM) performs up-sampling to add useful nodes to the sparse graph, while the strong node module (SNM) performs down-sampling based on strong node information and original features. Furthermore, we also reconfigure the RSRL (Recursive and Scalable Reinforcement Learning framework) module to improve fraud detection performance by increasing inter-class distances and decreasing intra-class distances, resulting in a refined decision boundary for optimized algorithmic efficacy. We use three metrics (AUC, recall, and G_Mean) to evaluate the performance of SCN_GNN. The experimental results compared with the state-of-the-art models on two real-world datasets demonstrate the superiority of the proposed SCN_GNN." @default.
- W4386965067 created "2023-09-23" @default.
- W4386965067 creator A5012104040 @default.
- W4386965067 creator A5015242847 @default.
- W4386965067 creator A5035742417 @default.
- W4386965067 creator A5058561724 @default.
- W4386965067 creator A5068597980 @default.
- W4386965067 creator A5078060785 @default.
- W4386965067 date "2024-03-01" @default.
- W4386965067 modified "2023-10-11" @default.
- W4386965067 title "SCN_GNN: A GNN-based fraud detection algorithm combining strong node and graph topology information" @default.
- W4386965067 cites W2064058256 @default.
- W4386965067 cites W2136891251 @default.
- W4386965067 cites W2588358651 @default.
- W4386965067 cites W2738130394 @default.
- W4386965067 cites W2945996535 @default.
- W4386965067 cites W2997128522 @default.
- W4386965067 cites W3016757214 @default.
- W4386965067 cites W3021651554 @default.
- W4386965067 cites W3068123808 @default.
- W4386965067 cites W3098259638 @default.
- W4386965067 cites W3099064659 @default.
- W4386965067 cites W3099825604 @default.
- W4386965067 cites W3124524575 @default.
- W4386965067 cites W3153858161 @default.
- W4386965067 cites W3156449551 @default.
- W4386965067 cites W3173820267 @default.
- W4386965067 cites W3175156831 @default.
- W4386965067 cites W3217103056 @default.
- W4386965067 cites W4206218111 @default.
- W4386965067 cites W4206991245 @default.
- W4386965067 cites W4224310669 @default.
- W4386965067 cites W4224319742 @default.
- W4386965067 cites W4283211166 @default.
- W4386965067 cites W4294192778 @default.
- W4386965067 cites W4306317259 @default.
- W4386965067 cites W4310117707 @default.
- W4386965067 cites W4311711472 @default.
- W4386965067 cites W4312126067 @default.
- W4386965067 doi "https://doi.org/10.1016/j.eswa.2023.121643" @default.
- W4386965067 hasPublicationYear "2024" @default.
- W4386965067 type Work @default.
- W4386965067 citedByCount "0" @default.
- W4386965067 crossrefType "journal-article" @default.
- W4386965067 hasAuthorship W4386965067A5012104040 @default.
- W4386965067 hasAuthorship W4386965067A5015242847 @default.
- W4386965067 hasAuthorship W4386965067A5035742417 @default.
- W4386965067 hasAuthorship W4386965067A5058561724 @default.
- W4386965067 hasAuthorship W4386965067A5068597980 @default.
- W4386965067 hasAuthorship W4386965067A5078060785 @default.
- W4386965067 hasConcept C124101348 @default.
- W4386965067 hasConcept C127413603 @default.
- W4386965067 hasConcept C132525143 @default.
- W4386965067 hasConcept C153180895 @default.
- W4386965067 hasConcept C154945302 @default.
- W4386965067 hasConcept C41008148 @default.
- W4386965067 hasConcept C48044578 @default.
- W4386965067 hasConcept C62611344 @default.
- W4386965067 hasConcept C66938386 @default.
- W4386965067 hasConcept C77088390 @default.
- W4386965067 hasConcept C80444323 @default.
- W4386965067 hasConceptScore W4386965067C124101348 @default.
- W4386965067 hasConceptScore W4386965067C127413603 @default.
- W4386965067 hasConceptScore W4386965067C132525143 @default.
- W4386965067 hasConceptScore W4386965067C153180895 @default.
- W4386965067 hasConceptScore W4386965067C154945302 @default.
- W4386965067 hasConceptScore W4386965067C41008148 @default.
- W4386965067 hasConceptScore W4386965067C48044578 @default.
- W4386965067 hasConceptScore W4386965067C62611344 @default.
- W4386965067 hasConceptScore W4386965067C66938386 @default.
- W4386965067 hasConceptScore W4386965067C77088390 @default.
- W4386965067 hasConceptScore W4386965067C80444323 @default.
- W4386965067 hasFunder F4320322843 @default.
- W4386965067 hasLocation W43869650671 @default.
- W4386965067 hasOpenAccess W4386965067 @default.
- W4386965067 hasPrimaryLocation W43869650671 @default.
- W4386965067 hasRelatedWork W1838576100 @default.
- W4386965067 hasRelatedWork W1983399550 @default.
- W4386965067 hasRelatedWork W2089704382 @default.
- W4386965067 hasRelatedWork W2095886385 @default.
- W4386965067 hasRelatedWork W2357523926 @default.
- W4386965067 hasRelatedWork W2389214306 @default.
- W4386965067 hasRelatedWork W2965083567 @default.
- W4386965067 hasRelatedWork W3151146928 @default.
- W4386965067 hasRelatedWork W4235240664 @default.
- W4386965067 hasRelatedWork W97075385 @default.
- W4386965067 hasVolume "237" @default.
- W4386965067 isParatext "false" @default.
- W4386965067 isRetracted "false" @default.
- W4386965067 workType "article" @default.