FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2903665338> ?p ?o ?g. }

• W2903665338 endingPage "565" @default.
• W2903665338 startingPage "555" @default.
• W2903665338 abstract "Recommendation systems have become ubiquitous in online shopping in recent decades due to their power in reducing excessive choices of customers and industries. Recent collaborative filtering methods based on the deep neural network are studied and introduce promising results due to their power in learning hidden representations for users and items. However, it has revealed its vulnerabilities under malicious user attacks. With the knowledge of a collaborative filtering algorithm and its parameters, the performance of this recommendation system can be easily downgraded. Unfortunately, this problem is not addressed well, and the study on defending recommendation systems is insufficient. In this paper, we aim to improve the robustness of recommendation systems based on two concepts - stage-wise hints training and randomness. To protect a target model, we introduce noise layers in the training of a target model to increase its resistance to adversarial perturbations. To reduce the noise layers' influence on model performance, we introduce intermediate layer outputs as hints from a teacher model to regularize the intermediate layers of a student target model. We consider white box attacks under which attackers have the knowledge of the target model. The generalizability and robustness properties of our method have been analytically inspected in experiments and discussions, and the computational cost is comparable to training a standard neural network-based collaborative filtering model. Through our investigation, the proposed defensive method can reduce the success rate of malicious user attacks and keep the prediction accuracy comparable to standard neural recommendation systems." @default.
• W2903665338 created "2018-12-22" @default.
• W2903665338 creator A5001529504 @default.
• W2903665338 creator A5002080576 @default.
• W2903665338 creator A5030837133 @default.
• W2903665338 creator A5044959745 @default.
• W2903665338 creator A5051764626 @default.
• W2903665338 creator A5074103823 @default.
• W2903665338 date "2019-03-01" @default.
• W2903665338 modified "2023-10-15" @default.
• W2903665338 title "Enhancing the Robustness of Neural Collaborative Filtering Systems Under Malicious Attacks" @default.
• W2903665338 cites W1720514416 @default.
• W2903665338 cites W1873407489 @default.
• W2903665338 cites W1903001680 @default.
• W2903665338 cites W1976618413 @default.
• W2903665338 cites W2014237985 @default.
• W2903665338 cites W2028988057 @default.
• W2903665338 cites W2054141820 @default.
• W2903665338 cites W2055928229 @default.
• W2903665338 cites W2061873838 @default.
• W2903665338 cites W2072651985 @default.
• W2903665338 cites W2085040216 @default.
• W2903665338 cites W2099866409 @default.
• W2903665338 cites W2103496339 @default.
• W2903665338 cites W2143995004 @default.
• W2903665338 cites W2157881433 @default.
• W2903665338 cites W2158121106 @default.
• W2903665338 cites W2159094788 @default.
• W2903665338 cites W2180612164 @default.
• W2903665338 cites W2219888463 @default.
• W2903665338 cites W2345837149 @default.
• W2903665338 cites W2559325834 @default.
• W2903665338 cites W2582558662 @default.
• W2903665338 cites W2601157141 @default.
• W2903665338 cites W2605350416 @default.
• W2903665338 cites W2740211889 @default.
• W2903665338 cites W2741249253 @default.
• W2903665338 cites W2762353177 @default.
• W2903665338 cites W2775637101 @default.
• W2903665338 cites W2808668169 @default.
• W2903665338 cites W2894761219 @default.
• W2903665338 cites W2913944796 @default.
• W2903665338 cites W2963857521 @default.
• W2903665338 cites W2964082701 @default.
• W2903665338 cites W4231109964 @default.
• W2903665338 doi "https://doi.org/10.1109/tmm.2018.2887018" @default.
• W2903665338 hasPublicationYear "2019" @default.
• W2903665338 type Work @default.
• W2903665338 sameAs 2903665338 @default.
• W2903665338 citedByCount "33" @default.
• W2903665338 countsByYear W29036653382018 @default.
• W2903665338 countsByYear W29036653382019 @default.
• W2903665338 countsByYear W29036653382020 @default.
• W2903665338 countsByYear W29036653382021 @default.
• W2903665338 countsByYear W29036653382022 @default.
• W2903665338 countsByYear W29036653382023 @default.
• W2903665338 crossrefType "journal-article" @default.
• W2903665338 hasAuthorship W2903665338A5001529504 @default.
• W2903665338 hasAuthorship W2903665338A5002080576 @default.
• W2903665338 hasAuthorship W2903665338A5030837133 @default.
• W2903665338 hasAuthorship W2903665338A5044959745 @default.
• W2903665338 hasAuthorship W2903665338A5051764626 @default.
• W2903665338 hasAuthorship W2903665338A5074103823 @default.
• W2903665338 hasBestOaLocation W29036653382 @default.
• W2903665338 hasConcept C104317684 @default.
• W2903665338 hasConcept C105795698 @default.
• W2903665338 hasConcept C119857082 @default.
• W2903665338 hasConcept C124101348 @default.
• W2903665338 hasConcept C154945302 @default.
• W2903665338 hasConcept C185592680 @default.
• W2903665338 hasConcept C21569690 @default.
• W2903665338 hasConcept C27158222 @default.
• W2903665338 hasConcept C33923547 @default.
• W2903665338 hasConcept C38652104 @default.
• W2903665338 hasConcept C41008148 @default.
• W2903665338 hasConcept C50644808 @default.
• W2903665338 hasConcept C55493867 @default.
• W2903665338 hasConcept C557471498 @default.
• W2903665338 hasConcept C63479239 @default.
• W2903665338 hasConcept C65856478 @default.
• W2903665338 hasConceptScore W2903665338C104317684 @default.
• W2903665338 hasConceptScore W2903665338C105795698 @default.
• W2903665338 hasConceptScore W2903665338C119857082 @default.
• W2903665338 hasConceptScore W2903665338C124101348 @default.
• W2903665338 hasConceptScore W2903665338C154945302 @default.
• W2903665338 hasConceptScore W2903665338C185592680 @default.
• W2903665338 hasConceptScore W2903665338C21569690 @default.
• W2903665338 hasConceptScore W2903665338C27158222 @default.
• W2903665338 hasConceptScore W2903665338C33923547 @default.
• W2903665338 hasConceptScore W2903665338C38652104 @default.
• W2903665338 hasConceptScore W2903665338C41008148 @default.
• W2903665338 hasConceptScore W2903665338C50644808 @default.
• W2903665338 hasConceptScore W2903665338C55493867 @default.
• W2903665338 hasConceptScore W2903665338C557471498 @default.
• W2903665338 hasConceptScore W2903665338C63479239 @default.
• W2903665338 hasConceptScore W2903665338C65856478 @default.
• W2903665338 hasFunder F4320321001 @default.
• W2903665338 hasFunder F4320334704 @default.

• next