Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306407769> ?p ?o ?g. }
- W4306407769 endingPage "28" @default.
- W4306407769 startingPage "1" @default.
- W4306407769 abstract "Neural graph collaborative filtering has received great recent attention due to its power of encoding the high-order neighborhood via the backbone graph neural networks. However, their robustness against noisy user-item interactions remains largely unexplored. Existing work on robust collaborative filtering mainly improves the robustness by denoising the graph structure, while recent progress in other fields has shown that directly adding adversarial perturbations in the embedding space can significantly improve the model robustness. In this work, we propose to improve the robustness of neural graph collaborative filtering via both denoising in the structure space and perturbing in the embedding space. Specifically, in the structure space, we measure the reliability of interactions and further use it to affect the message propagation process of the backbone graph neural networks; in the embedding space, we add in-distribution perturbations by mimicking the behavior of adversarial attacks and further combine it with contrastive learning to improve the performance. Extensive experiments have been conducted on four benchmark datasets to evaluate the effectiveness and efficiency of the proposed approach. The results demonstrate that the proposed approach outperforms the recent neural graph collaborative filtering methods especially when there are injected noisy interactions in the training data." @default.
- W4306407769 created "2022-10-17" @default.
- W4306407769 creator A5024682828 @default.
- W4306407769 creator A5034419036 @default.
- W4306407769 creator A5068043486 @default.
- W4306407769 creator A5068643894 @default.
- W4306407769 date "2023-02-07" @default.
- W4306407769 modified "2023-10-14" @default.
- W4306407769 title "Towards Robust Neural Graph Collaborative Filtering via Structure Denoising and Embedding Perturbation" @default.
- W4306407769 cites W1486317198 @default.
- W4306407769 cites W1536558110 @default.
- W4306407769 cites W1977290284 @default.
- W4306407769 cites W2027731328 @default.
- W4306407769 cites W2056021151 @default.
- W4306407769 cites W2090641502 @default.
- W4306407769 cites W2100235918 @default.
- W4306407769 cites W2101409192 @default.
- W4306407769 cites W2108415592 @default.
- W4306407769 cites W2110953678 @default.
- W4306407769 cites W2130354913 @default.
- W4306407769 cites W2219888463 @default.
- W4306407769 cites W2253995343 @default.
- W4306407769 cites W2605350416 @default.
- W4306407769 cites W2803831897 @default.
- W4306407769 cites W2972646741 @default.
- W4306407769 cites W2972657244 @default.
- W4306407769 cites W3012816161 @default.
- W4306407769 cites W3033630125 @default.
- W4306407769 cites W3035588407 @default.
- W4306407769 cites W3035589558 @default.
- W4306407769 cites W3045200674 @default.
- W4306407769 cites W3080292067 @default.
- W4306407769 cites W3093741743 @default.
- W4306407769 cites W3094127838 @default.
- W4306407769 cites W3100278010 @default.
- W4306407769 cites W3100324210 @default.
- W4306407769 cites W3104956872 @default.
- W4306407769 cites W3153325943 @default.
- W4306407769 cites W3154113024 @default.
- W4306407769 cites W3155299750 @default.
- W4306407769 cites W3156833186 @default.
- W4306407769 cites W3170682786 @default.
- W4306407769 cites W3172854437 @default.
- W4306407769 cites W3173365306 @default.
- W4306407769 cites W3178807794 @default.
- W4306407769 cites W3178835722 @default.
- W4306407769 cites W3206458369 @default.
- W4306407769 cites W3208227120 @default.
- W4306407769 cites W4210257598 @default.
- W4306407769 cites W4288280739 @default.
- W4306407769 doi "https://doi.org/10.1145/3568396" @default.
- W4306407769 hasPublicationYear "2023" @default.
- W4306407769 type Work @default.
- W4306407769 citedByCount "1" @default.
- W4306407769 countsByYear W43064077692023 @default.
- W4306407769 crossrefType "journal-article" @default.
- W4306407769 hasAuthorship W4306407769A5024682828 @default.
- W4306407769 hasAuthorship W4306407769A5034419036 @default.
- W4306407769 hasAuthorship W4306407769A5068043486 @default.
- W4306407769 hasAuthorship W4306407769A5068643894 @default.
- W4306407769 hasConcept C104317684 @default.
- W4306407769 hasConcept C119857082 @default.
- W4306407769 hasConcept C132525143 @default.
- W4306407769 hasConcept C153180895 @default.
- W4306407769 hasConcept C154945302 @default.
- W4306407769 hasConcept C185592680 @default.
- W4306407769 hasConcept C21569690 @default.
- W4306407769 hasConcept C41008148 @default.
- W4306407769 hasConcept C41608201 @default.
- W4306407769 hasConcept C50644808 @default.
- W4306407769 hasConcept C55493867 @default.
- W4306407769 hasConcept C557471498 @default.
- W4306407769 hasConcept C63479239 @default.
- W4306407769 hasConcept C75564084 @default.
- W4306407769 hasConcept C80444323 @default.
- W4306407769 hasConceptScore W4306407769C104317684 @default.
- W4306407769 hasConceptScore W4306407769C119857082 @default.
- W4306407769 hasConceptScore W4306407769C132525143 @default.
- W4306407769 hasConceptScore W4306407769C153180895 @default.
- W4306407769 hasConceptScore W4306407769C154945302 @default.
- W4306407769 hasConceptScore W4306407769C185592680 @default.
- W4306407769 hasConceptScore W4306407769C21569690 @default.
- W4306407769 hasConceptScore W4306407769C41008148 @default.
- W4306407769 hasConceptScore W4306407769C41608201 @default.
- W4306407769 hasConceptScore W4306407769C50644808 @default.
- W4306407769 hasConceptScore W4306407769C55493867 @default.
- W4306407769 hasConceptScore W4306407769C557471498 @default.
- W4306407769 hasConceptScore W4306407769C63479239 @default.
- W4306407769 hasConceptScore W4306407769C75564084 @default.
- W4306407769 hasConceptScore W4306407769C80444323 @default.
- W4306407769 hasFunder F4320335777 @default.
- W4306407769 hasIssue "3" @default.
- W4306407769 hasLocation W43064077691 @default.
- W4306407769 hasOpenAccess W4306407769 @default.
- W4306407769 hasPrimaryLocation W43064077691 @default.
- W4306407769 hasRelatedWork W1484355083 @default.
- W4306407769 hasRelatedWork W2041004656 @default.
- W4306407769 hasRelatedWork W2098758514 @default.