Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386427396> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4386427396 abstract "To select appropriate web services for users, the Quality-of-Service (QoS) based collaborative prediction models are widely used. Despite the success of collaborative prediction models in selecting appropriate web services for users, existing models do not take into account the users' authority to manage their own generated data as stipulated by many privacy-preserving regulations, such as the General Data Protection Regulation (GDPR) and California Consumer Privacy Act (CCPA). Moreover, unlearning is urgently needed due to the security concerns such as data poisoning attacks. Existing QoS prediction methods are not optimized for unlearning, suffering from low model availability when handling unlearning requests by full re-training. To address this problem, we propose QoSEraser: a novel efficient machine unlearning framework for QoS prediction tasks. The central concepts of the QoSEraser involve: (1) dividing the training data into multiple shards to train submodels according to the cluster results on graph embeddings induced by random walk on contextual information graph. Such division ensures the preservation of collaborative signals in collected QoS records; (2) a concatenate aggregation method and a stacking & attention-based aggregation method are used to condense information in fragmented embeddings to a uniform one adaptively. Experiments on large-scale datasets show that QoSEraser achieves efficient forgetting learning and outperforms state-of-the-art unlearning approaches in terms of performance. Source codes are available at https://github.com/ZengYuXiang7/QoSEraser." @default.
- W4386427396 created "2023-09-05" @default.
- W4386427396 creator A5005015081 @default.
- W4386427396 creator A5007951793 @default.
- W4386427396 creator A5023419869 @default.
- W4386427396 creator A5043416563 @default.
- W4386427396 creator A5070584261 @default.
- W4386427396 creator A5076453587 @default.
- W4386427396 creator A5092739982 @default.
- W4386427396 date "2023-07-01" @default.
- W4386427396 modified "2023-09-30" @default.
- W4386427396 title "QoSEraser: A Data Erasable Framework for Web Service QoS Prediction" @default.
- W4386427396 cites W1965310012 @default.
- W4386427396 cites W2026749761 @default.
- W4386427396 cites W2030239032 @default.
- W4386427396 cites W2034405392 @default.
- W4386427396 cites W2037111396 @default.
- W4386427396 cites W2042690527 @default.
- W4386427396 cites W2054141820 @default.
- W4386427396 cites W2072191819 @default.
- W4386427396 cites W2091381870 @default.
- W4386427396 cites W2109637792 @default.
- W4386427396 cites W2130551617 @default.
- W4386427396 cites W2161160262 @default.
- W4386427396 cites W2605350416 @default.
- W4386427396 cites W2738639449 @default.
- W4386427396 cites W2911126749 @default.
- W4386427396 cites W2962756421 @default.
- W4386427396 cites W2997532515 @default.
- W4386427396 cites W3004443750 @default.
- W4386427396 cites W3095155273 @default.
- W4386427396 cites W3154155772 @default.
- W4386427396 cites W3162576365 @default.
- W4386427396 cites W3175430527 @default.
- W4386427396 cites W3176739818 @default.
- W4386427396 cites W3213826430 @default.
- W4386427396 cites W4296562799 @default.
- W4386427396 cites W4302275239 @default.
- W4386427396 doi "https://doi.org/10.1109/sse60056.2023.00022" @default.
- W4386427396 hasPublicationYear "2023" @default.
- W4386427396 type Work @default.
- W4386427396 citedByCount "0" @default.
- W4386427396 crossrefType "proceedings-article" @default.
- W4386427396 hasAuthorship W4386427396A5005015081 @default.
- W4386427396 hasAuthorship W4386427396A5007951793 @default.
- W4386427396 hasAuthorship W4386427396A5023419869 @default.
- W4386427396 hasAuthorship W4386427396A5043416563 @default.
- W4386427396 hasAuthorship W4386427396A5070584261 @default.
- W4386427396 hasAuthorship W4386427396A5076453587 @default.
- W4386427396 hasAuthorship W4386427396A5092739982 @default.
- W4386427396 hasConcept C119857082 @default.
- W4386427396 hasConcept C124101348 @default.
- W4386427396 hasConcept C132525143 @default.
- W4386427396 hasConcept C136764020 @default.
- W4386427396 hasConcept C31258907 @default.
- W4386427396 hasConcept C35578498 @default.
- W4386427396 hasConcept C41008148 @default.
- W4386427396 hasConcept C5119721 @default.
- W4386427396 hasConcept C80444323 @default.
- W4386427396 hasConceptScore W4386427396C119857082 @default.
- W4386427396 hasConceptScore W4386427396C124101348 @default.
- W4386427396 hasConceptScore W4386427396C132525143 @default.
- W4386427396 hasConceptScore W4386427396C136764020 @default.
- W4386427396 hasConceptScore W4386427396C31258907 @default.
- W4386427396 hasConceptScore W4386427396C35578498 @default.
- W4386427396 hasConceptScore W4386427396C41008148 @default.
- W4386427396 hasConceptScore W4386427396C5119721 @default.
- W4386427396 hasConceptScore W4386427396C80444323 @default.
- W4386427396 hasFunder F4320309778 @default.
- W4386427396 hasLocation W43864273961 @default.
- W4386427396 hasOpenAccess W4386427396 @default.
- W4386427396 hasPrimaryLocation W43864273961 @default.
- W4386427396 hasRelatedWork W1604044397 @default.
- W4386427396 hasRelatedWork W1608069547 @default.
- W4386427396 hasRelatedWork W2123032963 @default.
- W4386427396 hasRelatedWork W2156659186 @default.
- W4386427396 hasRelatedWork W2353072801 @default.
- W4386427396 hasRelatedWork W2360066791 @default.
- W4386427396 hasRelatedWork W2365367704 @default.
- W4386427396 hasRelatedWork W2372698109 @default.
- W4386427396 hasRelatedWork W2810716635 @default.
- W4386427396 hasRelatedWork W2978318576 @default.
- W4386427396 isParatext "false" @default.
- W4386427396 isRetracted "false" @default.
- W4386427396 workType "article" @default.