Matches in SemOpenAlex for { <https://semopenalex.org/work/W4372266857> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4372266857 abstract "Risk item identification is vital for protecting the health of ecommerce trades. Existing solutions prefer to model structure information besides item attributes and optimize parameters in cross-entropy (CE) manners. However, the few labeled and imbalanced supervision in real-world scenarios usually results in poor generalization of CE optimization. More seriously, the pattern-level difference of risk items is often neglected in binary supervised learning, leading to limited performance. In this paper, we propose a novel Clustering-based Supervised Contrastive Learning (CSCL) to address the two challenges. CSCL first devises a contrastive heterogeneous graph neural network that fully exploits multiple risk relations in contrastive learning, keeping generalization performance. It then designs a clustering-based reweighted sampling strategy to search informative positive and negative training instances for effective pattern-level optimization. We test the performance on Xianyu Platform, and experimental results demonstrate that CSCL outperforms all baselines." @default.
- W4372266857 created "2023-05-07" @default.
- W4372266857 creator A5026475770 @default.
- W4372266857 creator A5051805730 @default.
- W4372266857 creator A5053509334 @default.
- W4372266857 creator A5056036725 @default.
- W4372266857 creator A5058010200 @default.
- W4372266857 creator A5074614306 @default.
- W4372266857 date "2023-06-04" @default.
- W4372266857 modified "2023-09-29" @default.
- W4372266857 title "Clustering-Based Supervised Contrastive Learning for Identifying Risk Items on Heterogeneous Graph" @default.
- W4372266857 cites W2132202037 @default.
- W4372266857 cites W2965857891 @default.
- W4372266857 cites W3012871709 @default.
- W4372266857 cites W3172710079 @default.
- W4372266857 cites W3177203410 @default.
- W4372266857 cites W3209009171 @default.
- W4372266857 doi "https://doi.org/10.1109/icassp49357.2023.10094817" @default.
- W4372266857 hasPublicationYear "2023" @default.
- W4372266857 type Work @default.
- W4372266857 citedByCount "0" @default.
- W4372266857 crossrefType "proceedings-article" @default.
- W4372266857 hasAuthorship W4372266857A5026475770 @default.
- W4372266857 hasAuthorship W4372266857A5051805730 @default.
- W4372266857 hasAuthorship W4372266857A5053509334 @default.
- W4372266857 hasAuthorship W4372266857A5056036725 @default.
- W4372266857 hasAuthorship W4372266857A5058010200 @default.
- W4372266857 hasAuthorship W4372266857A5074614306 @default.
- W4372266857 hasBestOaLocation W43722668571 @default.
- W4372266857 hasConcept C106301342 @default.
- W4372266857 hasConcept C119857082 @default.
- W4372266857 hasConcept C121332964 @default.
- W4372266857 hasConcept C12267149 @default.
- W4372266857 hasConcept C124101348 @default.
- W4372266857 hasConcept C132525143 @default.
- W4372266857 hasConcept C134306372 @default.
- W4372266857 hasConcept C136389625 @default.
- W4372266857 hasConcept C153180895 @default.
- W4372266857 hasConcept C154945302 @default.
- W4372266857 hasConcept C165696696 @default.
- W4372266857 hasConcept C167981619 @default.
- W4372266857 hasConcept C177148314 @default.
- W4372266857 hasConcept C33923547 @default.
- W4372266857 hasConcept C38652104 @default.
- W4372266857 hasConcept C41008148 @default.
- W4372266857 hasConcept C50644808 @default.
- W4372266857 hasConcept C62520636 @default.
- W4372266857 hasConcept C66905080 @default.
- W4372266857 hasConcept C73555534 @default.
- W4372266857 hasConcept C80444323 @default.
- W4372266857 hasConceptScore W4372266857C106301342 @default.
- W4372266857 hasConceptScore W4372266857C119857082 @default.
- W4372266857 hasConceptScore W4372266857C121332964 @default.
- W4372266857 hasConceptScore W4372266857C12267149 @default.
- W4372266857 hasConceptScore W4372266857C124101348 @default.
- W4372266857 hasConceptScore W4372266857C132525143 @default.
- W4372266857 hasConceptScore W4372266857C134306372 @default.
- W4372266857 hasConceptScore W4372266857C136389625 @default.
- W4372266857 hasConceptScore W4372266857C153180895 @default.
- W4372266857 hasConceptScore W4372266857C154945302 @default.
- W4372266857 hasConceptScore W4372266857C165696696 @default.
- W4372266857 hasConceptScore W4372266857C167981619 @default.
- W4372266857 hasConceptScore W4372266857C177148314 @default.
- W4372266857 hasConceptScore W4372266857C33923547 @default.
- W4372266857 hasConceptScore W4372266857C38652104 @default.
- W4372266857 hasConceptScore W4372266857C41008148 @default.
- W4372266857 hasConceptScore W4372266857C50644808 @default.
- W4372266857 hasConceptScore W4372266857C62520636 @default.
- W4372266857 hasConceptScore W4372266857C66905080 @default.
- W4372266857 hasConceptScore W4372266857C73555534 @default.
- W4372266857 hasConceptScore W4372266857C80444323 @default.
- W4372266857 hasFunder F4320321001 @default.
- W4372266857 hasLocation W43722668571 @default.
- W4372266857 hasOpenAccess W4372266857 @default.
- W4372266857 hasPrimaryLocation W43722668571 @default.
- W4372266857 hasRelatedWork W3046775127 @default.
- W4372266857 hasRelatedWork W3094076422 @default.
- W4372266857 hasRelatedWork W3133593829 @default.
- W4372266857 hasRelatedWork W3162567751 @default.
- W4372266857 hasRelatedWork W3215867059 @default.
- W4372266857 hasRelatedWork W4220686584 @default.
- W4372266857 hasRelatedWork W4221088574 @default.
- W4372266857 hasRelatedWork W4285260836 @default.
- W4372266857 hasRelatedWork W4319309271 @default.
- W4372266857 hasRelatedWork W4322008322 @default.
- W4372266857 isParatext "false" @default.
- W4372266857 isRetracted "false" @default.
- W4372266857 workType "article" @default.