Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205823564> ?p ?o ?g. }
- W4205823564 endingPage "102814" @default.
- W4205823564 startingPage "102814" @default.
- W4205823564 abstract "With the rapid development of social media and big data technology, user’s sequence behavior information can be well recorded and preserved on different media platforms. It is crucial to model the user preference through mining their sequential behaviors. The goal of sequential recommendation is to predict what a user may interact with in the next moment based on the user’s historical record of interactive sequence. However, existing sequential recommendation methods generally adopt a negative sampling mechanism (e.g. random and uniform sampling) for the pairwise learning, which brings the defect of insufficient training to the model, and decrease the evaluation performance of the entire model. Therefore, we propose a Non-sampling Self-attentive Sequential Recommendation (NSSR) model that combines non-sampling mechanism and self-attention mechanism. Under the premise of ensuring the efficient training of the model, NSSR model takes all pairs in the training set as training samples, so as to achieve the goal of fully training the model. Specifically, we take the interactive sequence as the current user representation, and propose a new loss function to implement the non-sampling training mechanism. Finally, the state-of-the-art result is achieved on three public datasets, Movielens-1M, Amazon Beauty and Foursquare_TKY, and the recommendation performance increase by about 29.3%, 25.7% and 42.1% respectively." @default.
- W4205823564 created "2022-01-25" @default.
- W4205823564 creator A5014825654 @default.
- W4205823564 creator A5017621102 @default.
- W4205823564 creator A5052591163 @default.
- W4205823564 creator A5058073103 @default.
- W4205823564 creator A5079805574 @default.
- W4205823564 date "2022-03-01" @default.
- W4205823564 modified "2023-10-16" @default.
- W4205823564 title "Combining Non-sampling and Self-attention for Sequential Recommendation" @default.
- W4205823564 cites W1886704267 @default.
- W4205823564 cites W1972436494 @default.
- W4205823564 cites W1995797952 @default.
- W4205823564 cites W2017921654 @default.
- W4205823564 cites W2099970131 @default.
- W4205823564 cites W2171279286 @default.
- W4205823564 cites W2189936406 @default.
- W4205823564 cites W2194775991 @default.
- W4205823564 cites W2319598986 @default.
- W4205823564 cites W2334831412 @default.
- W4205823564 cites W2340502990 @default.
- W4205823564 cites W2539781657 @default.
- W4205823564 cites W2558751478 @default.
- W4205823564 cites W2605350416 @default.
- W4205823564 cites W2728796024 @default.
- W4205823564 cites W2734755249 @default.
- W4205823564 cites W2743289629 @default.
- W4205823564 cites W2750303327 @default.
- W4205823564 cites W2755570041 @default.
- W4205823564 cites W2762735242 @default.
- W4205823564 cites W2783272285 @default.
- W4205823564 cites W2788114581 @default.
- W4205823564 cites W2793148563 @default.
- W4205823564 cites W2969961114 @default.
- W4205823564 cites W2996931760 @default.
- W4205823564 cites W2997261254 @default.
- W4205823564 cites W2999309750 @default.
- W4205823564 cites W3012391712 @default.
- W4205823564 cites W3014900199 @default.
- W4205823564 cites W3015126766 @default.
- W4205823564 cites W3035308866 @default.
- W4205823564 cites W3100917752 @default.
- W4205823564 cites W3101707147 @default.
- W4205823564 cites W3105472188 @default.
- W4205823564 cites W3106445281 @default.
- W4205823564 cites W3120060780 @default.
- W4205823564 cites W3132970391 @default.
- W4205823564 cites W3176074827 @default.
- W4205823564 cites W3211356784 @default.
- W4205823564 cites W4297971002 @default.
- W4205823564 cites W1966894722 @default.
- W4205823564 doi "https://doi.org/10.1016/j.ipm.2021.102814" @default.
- W4205823564 hasPublicationYear "2022" @default.
- W4205823564 type Work @default.
- W4205823564 citedByCount "6" @default.
- W4205823564 countsByYear W42058235642022 @default.
- W4205823564 countsByYear W42058235642023 @default.
- W4205823564 crossrefType "journal-article" @default.
- W4205823564 hasAuthorship W4205823564A5014825654 @default.
- W4205823564 hasAuthorship W4205823564A5017621102 @default.
- W4205823564 hasAuthorship W4205823564A5052591163 @default.
- W4205823564 hasAuthorship W4205823564A5058073103 @default.
- W4205823564 hasAuthorship W4205823564A5079805574 @default.
- W4205823564 hasConcept C106131492 @default.
- W4205823564 hasConcept C111472728 @default.
- W4205823564 hasConcept C119857082 @default.
- W4205823564 hasConcept C121332964 @default.
- W4205823564 hasConcept C124101348 @default.
- W4205823564 hasConcept C138885662 @default.
- W4205823564 hasConcept C140779682 @default.
- W4205823564 hasConcept C154945302 @default.
- W4205823564 hasConcept C15744967 @default.
- W4205823564 hasConcept C177264268 @default.
- W4205823564 hasConcept C17744445 @default.
- W4205823564 hasConcept C179254644 @default.
- W4205823564 hasConcept C184898388 @default.
- W4205823564 hasConcept C199360897 @default.
- W4205823564 hasConcept C199539241 @default.
- W4205823564 hasConcept C21569690 @default.
- W4205823564 hasConcept C2776156558 @default.
- W4205823564 hasConcept C2776359362 @default.
- W4205823564 hasConcept C2778112365 @default.
- W4205823564 hasConcept C31972630 @default.
- W4205823564 hasConcept C41008148 @default.
- W4205823564 hasConcept C54355233 @default.
- W4205823564 hasConcept C557471498 @default.
- W4205823564 hasConcept C65499552 @default.
- W4205823564 hasConcept C74650414 @default.
- W4205823564 hasConcept C77805123 @default.
- W4205823564 hasConcept C86803240 @default.
- W4205823564 hasConcept C89611455 @default.
- W4205823564 hasConcept C94625758 @default.
- W4205823564 hasConceptScore W4205823564C106131492 @default.
- W4205823564 hasConceptScore W4205823564C111472728 @default.
- W4205823564 hasConceptScore W4205823564C119857082 @default.
- W4205823564 hasConceptScore W4205823564C121332964 @default.
- W4205823564 hasConceptScore W4205823564C124101348 @default.
- W4205823564 hasConceptScore W4205823564C138885662 @default.