Matches in SemOpenAlex for { <https://semopenalex.org/work/W2798713837> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2798713837 abstract "Latent Factor Models (LFMs) based on Collaborative Filtering (CF) have been widely applied in many recommendation systems, due to their good performance of prediction accuracy. In addition to users' ratings, auxiliary information such as item features is often used to improve performance, especially when ratings are very sparse. To the best of our knowledge, most existing LFMs integrate different item features in the same way for all users. Nevertheless, the attention on different item attributes varies a lot from user to user. For personalized recommendation, it is valuable to know what feature of an item a user cares most about. Besides, the latent vectors used to represent users or items in LFMs have few explicit meanings, which makes it difficult to explain why an item is recommended to a specific user. In this work, we propose the Attention-driven Factor Model (AFM), which can not only integrate item features driven by users' attention but also help answer this why. To estimate users' attention distributions on different item features, we propose the Gated Attention Units (GAUs) for AFM. The GAUs make it possible to let the latent factors talk, by generating user attention distributions from user latent vectors. With users' attention distributions, we can tune the weights of item features for different users. Moreover, users' attention distributions can also serve as explanations for our recommendations. Experiments on several real-world datasets demonstrate the advantages of AFM (using GAUs) over competitive baseline algorithms on rating prediction." @default.
- W2798713837 created "2018-05-07" @default.
- W2798713837 creator A5022678604 @default.
- W2798713837 creator A5041921496 @default.
- W2798713837 creator A5066061403 @default.
- W2798713837 creator A5068007462 @default.
- W2798713837 creator A5080935670 @default.
- W2798713837 creator A5091902436 @default.
- W2798713837 date "2018-06-27" @default.
- W2798713837 modified "2023-10-13" @default.
- W2798713837 title "Attention-driven Factor Model for Explainable Personalized Recommendation" @default.
- W2798713837 cites W2054141820 @default.
- W2798713837 cites W2085040216 @default.
- W2798713837 cites W2094286023 @default.
- W2798713837 cites W2152184085 @default.
- W2798713837 cites W2157881433 @default.
- W2798713837 cites W2295739661 @default.
- W2798713837 cites W2605350416 @default.
- W2798713837 cites W2741249238 @default.
- W2798713837 cites W2963323306 @default.
- W2798713837 doi "https://doi.org/10.1145/3209978.3210083" @default.
- W2798713837 hasPublicationYear "2018" @default.
- W2798713837 type Work @default.
- W2798713837 sameAs 2798713837 @default.
- W2798713837 citedByCount "40" @default.
- W2798713837 countsByYear W27987138372012 @default.
- W2798713837 countsByYear W27987138372019 @default.
- W2798713837 countsByYear W27987138372020 @default.
- W2798713837 countsByYear W27987138372021 @default.
- W2798713837 countsByYear W27987138372022 @default.
- W2798713837 countsByYear W27987138372023 @default.
- W2798713837 crossrefType "proceedings-article" @default.
- W2798713837 hasAuthorship W2798713837A5022678604 @default.
- W2798713837 hasAuthorship W2798713837A5041921496 @default.
- W2798713837 hasAuthorship W2798713837A5066061403 @default.
- W2798713837 hasAuthorship W2798713837A5068007462 @default.
- W2798713837 hasAuthorship W2798713837A5080935670 @default.
- W2798713837 hasAuthorship W2798713837A5091902436 @default.
- W2798713837 hasConcept C10879293 @default.
- W2798713837 hasConcept C111368507 @default.
- W2798713837 hasConcept C119857082 @default.
- W2798713837 hasConcept C124101348 @default.
- W2798713837 hasConcept C12725497 @default.
- W2798713837 hasConcept C127313418 @default.
- W2798713837 hasConcept C138885662 @default.
- W2798713837 hasConcept C154945302 @default.
- W2798713837 hasConcept C199360897 @default.
- W2798713837 hasConcept C21569690 @default.
- W2798713837 hasConcept C23123220 @default.
- W2798713837 hasConcept C2776401178 @default.
- W2798713837 hasConcept C2781039887 @default.
- W2798713837 hasConcept C41008148 @default.
- W2798713837 hasConcept C41895202 @default.
- W2798713837 hasConcept C557471498 @default.
- W2798713837 hasConceptScore W2798713837C10879293 @default.
- W2798713837 hasConceptScore W2798713837C111368507 @default.
- W2798713837 hasConceptScore W2798713837C119857082 @default.
- W2798713837 hasConceptScore W2798713837C124101348 @default.
- W2798713837 hasConceptScore W2798713837C12725497 @default.
- W2798713837 hasConceptScore W2798713837C127313418 @default.
- W2798713837 hasConceptScore W2798713837C138885662 @default.
- W2798713837 hasConceptScore W2798713837C154945302 @default.
- W2798713837 hasConceptScore W2798713837C199360897 @default.
- W2798713837 hasConceptScore W2798713837C21569690 @default.
- W2798713837 hasConceptScore W2798713837C23123220 @default.
- W2798713837 hasConceptScore W2798713837C2776401178 @default.
- W2798713837 hasConceptScore W2798713837C2781039887 @default.
- W2798713837 hasConceptScore W2798713837C41008148 @default.
- W2798713837 hasConceptScore W2798713837C41895202 @default.
- W2798713837 hasConceptScore W2798713837C557471498 @default.
- W2798713837 hasLocation W27987138371 @default.
- W2798713837 hasOpenAccess W2798713837 @default.
- W2798713837 hasPrimaryLocation W27987138371 @default.
- W2798713837 hasRelatedWork W1773619406 @default.
- W2798713837 hasRelatedWork W2004557467 @default.
- W2798713837 hasRelatedWork W2045663397 @default.
- W2798713837 hasRelatedWork W2348159088 @default.
- W2798713837 hasRelatedWork W2375487899 @default.
- W2798713837 hasRelatedWork W2402445420 @default.
- W2798713837 hasRelatedWork W2798451620 @default.
- W2798713837 hasRelatedWork W2897827065 @default.
- W2798713837 hasRelatedWork W2906884792 @default.
- W2798713837 hasRelatedWork W2972495023 @default.
- W2798713837 isParatext "false" @default.
- W2798713837 isRetracted "false" @default.
- W2798713837 magId "2798713837" @default.
- W2798713837 workType "article" @default.