Matches in SemOpenAlex for { <https://semopenalex.org/work/W2787512446> ?p ?o ?g. }
- W2787512446 abstract "We extend variational autoencoders (VAEs) to collaborative filtering for implicit feedback. This non-linear probabilistic model enables us to go beyond the limited modeling capacity of linear factor models which still largely dominate collaborative filtering research.We introduce a generative model with multinomial likelihood and use Bayesian inference for parameter estimation. Despite widespread use in language modeling and economics, the multinomial likelihood receives less attention in the recommender systems literature. We introduce a different regularization parameter for the learning objective, which proves to be crucial for achieving competitive performance. Remarkably, there is an efficient way to tune the parameter using annealing. The resulting model and learning algorithm has information-theoretic connections to maximum entropy discrimination and the information bottleneck principle. Empirically, we show that the proposed approach significantly outperforms several state-of-the-art baselines, including two recently-proposed neural network approaches, on several real-world datasets. We also provide extended experiments comparing the multinomial likelihood with other commonly used likelihood functions in the latent factor collaborative filtering literature and show favorable results. Finally, we identify the pros and cons of employing a principled Bayesian inference approach and characterize settings where it provides the most significant improvements." @default.
- W2787512446 created "2018-02-23" @default.
- W2787512446 creator A5068077704 @default.
- W2787512446 creator A5069219684 @default.
- W2787512446 creator A5073514348 @default.
- W2787512446 creator A5079882875 @default.
- W2787512446 date "2018-02-15" @default.
- W2787512446 modified "2023-09-26" @default.
- W2787512446 title "Variational Autoencoders for Collaborative Filtering" @default.
- W2787512446 cites W115367774 @default.
- W2787512446 cites W1516111018 @default.
- W2787512446 cites W1522301498 @default.
- W2787512446 cites W1550812296 @default.
- W2787512446 cites W1556219185 @default.
- W2787512446 cites W1720514416 @default.
- W2787512446 cites W1880262756 @default.
- W2787512446 cites W1909320841 @default.
- W2787512446 cites W1974318090 @default.
- W2787512446 cites W1987431925 @default.
- W2787512446 cites W2004657139 @default.
- W2787512446 cites W2069870183 @default.
- W2787512446 cites W2099866409 @default.
- W2787512446 cites W21006490 @default.
- W2787512446 cites W2101409192 @default.
- W2787512446 cites W2116802659 @default.
- W2787512446 cites W2118079529 @default.
- W2787512446 cites W2119384858 @default.
- W2787512446 cites W2124187902 @default.
- W2787512446 cites W2137028279 @default.
- W2787512446 cites W2140310134 @default.
- W2787512446 cites W2157881433 @default.
- W2787512446 cites W2161813919 @default.
- W2787512446 cites W2210838531 @default.
- W2787512446 cites W2253995343 @default.
- W2787512446 cites W2262817822 @default.
- W2787512446 cites W2400422027 @default.
- W2787512446 cites W2403286959 @default.
- W2787512446 cites W2409498980 @default.
- W2787512446 cites W2463645429 @default.
- W2787512446 cites W2467604901 @default.
- W2787512446 cites W2508504774 @default.
- W2787512446 cites W2512971201 @default.
- W2787512446 cites W2557579533 @default.
- W2787512446 cites W2654637199 @default.
- W2787512446 cites W2733115588 @default.
- W2787512446 cites W2753738274 @default.
- W2787512446 cites W2767072992 @default.
- W2787512446 cites W2949588817 @default.
- W2787512446 cites W2950133940 @default.
- W2787512446 cites W2951004968 @default.
- W2787512446 cites W2951707557 @default.
- W2787512446 cites W2953316038 @default.
- W2787512446 cites W2963773425 @default.
- W2787512446 cites W3101380508 @default.
- W2787512446 cites W3102701984 @default.
- W2787512446 doi "https://doi.org/10.48550/arxiv.1802.05814" @default.
- W2787512446 hasPublicationYear "2018" @default.
- W2787512446 type Work @default.
- W2787512446 sameAs 2787512446 @default.
- W2787512446 citedByCount "9" @default.
- W2787512446 countsByYear W27875124462018 @default.
- W2787512446 countsByYear W27875124462020 @default.
- W2787512446 crossrefType "posted-content" @default.
- W2787512446 hasAuthorship W2787512446A5068077704 @default.
- W2787512446 hasAuthorship W2787512446A5069219684 @default.
- W2787512446 hasAuthorship W2787512446A5073514348 @default.
- W2787512446 hasAuthorship W2787512446A5079882875 @default.
- W2787512446 hasBestOaLocation W27875124461 @default.
- W2787512446 hasConcept C105795698 @default.
- W2787512446 hasConcept C107673813 @default.
- W2787512446 hasConcept C119857082 @default.
- W2787512446 hasConcept C152139883 @default.
- W2787512446 hasConcept C154945302 @default.
- W2787512446 hasConcept C160234255 @default.
- W2787512446 hasConcept C185429906 @default.
- W2787512446 hasConcept C21569690 @default.
- W2787512446 hasConcept C2776135515 @default.
- W2787512446 hasConcept C2776214188 @default.
- W2787512446 hasConcept C33923547 @default.
- W2787512446 hasConcept C41008148 @default.
- W2787512446 hasConcept C557471498 @default.
- W2787512446 hasConcept C60008888 @default.
- W2787512446 hasConcept C95923904 @default.
- W2787512446 hasConcept C9679016 @default.
- W2787512446 hasConceptScore W2787512446C105795698 @default.
- W2787512446 hasConceptScore W2787512446C107673813 @default.
- W2787512446 hasConceptScore W2787512446C119857082 @default.
- W2787512446 hasConceptScore W2787512446C152139883 @default.
- W2787512446 hasConceptScore W2787512446C154945302 @default.
- W2787512446 hasConceptScore W2787512446C160234255 @default.
- W2787512446 hasConceptScore W2787512446C185429906 @default.
- W2787512446 hasConceptScore W2787512446C21569690 @default.
- W2787512446 hasConceptScore W2787512446C2776135515 @default.
- W2787512446 hasConceptScore W2787512446C2776214188 @default.
- W2787512446 hasConceptScore W2787512446C33923547 @default.
- W2787512446 hasConceptScore W2787512446C41008148 @default.
- W2787512446 hasConceptScore W2787512446C557471498 @default.
- W2787512446 hasConceptScore W2787512446C60008888 @default.
- W2787512446 hasConceptScore W2787512446C95923904 @default.
- W2787512446 hasConceptScore W2787512446C9679016 @default.