Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892821876> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2892821876 abstract "Sequential recommendation algorithms aim to predict users' future behavior given their historical interactions. A recent line of work has achieved state-of-the-art performance on sequential recommendation tasks by adapting ideas from metric learning and knowledge-graph completion. These algorithms replace inner products with low-dimensional embeddings and distance functions, employing a simple translation dynamic to model user behavior over time. In this paper, we propose TransFM, a model that combines translation and metric-based approaches for sequential recommendation with Factorization Machines (FMs). Doing so allows us to reap the benefits of FMs (in particular, the ability to straightforwardly incorporate content-based features), while enhancing the state-of-the-art performance of translation-based models in sequential settings. Specifically, we learn an embedding and translation space for each feature dimension, replacing the inner product with the squared Euclidean distance to measure the interaction strength between features. Like FMs, we show that the model equation for TransFM can be computed in linear time and optimized using classical techniques. As TransFM operates on arbitrary feature vectors, additional content information can be easily incorporated without significant changes to the model itself. Empirically, the performance of TransFM significantly increases when taking content features into account, outperforming state-of-the-art models on sequential recommendation tasks for a wide variety of datasets." @default.
- W2892821876 created "2018-10-05" @default.
- W2892821876 creator A5021827617 @default.
- W2892821876 creator A5052693492 @default.
- W2892821876 date "2018-09-27" @default.
- W2892821876 modified "2023-10-16" @default.
- W2892821876 title "Translation-based factorization machines for sequential recommendation" @default.
- W2892821876 cites W1984127251 @default.
- W2892821876 cites W1985854669 @default.
- W2892821876 cites W2006642624 @default.
- W2892821876 cites W2027731328 @default.
- W2892821876 cites W2077802345 @default.
- W2892821876 cites W2089791802 @default.
- W2892821876 cites W2171279286 @default.
- W2892821876 cites W2171619825 @default.
- W2892821876 cites W2295739661 @default.
- W2892821876 cites W2509893387 @default.
- W2892821876 cites W2512971201 @default.
- W2892821876 cites W2517523272 @default.
- W2892821876 cites W2583898301 @default.
- W2892821876 cites W2604438604 @default.
- W2892821876 cites W2629386751 @default.
- W2892821876 cites W2745534091 @default.
- W2892821876 cites W2964352502 @default.
- W2892821876 doi "https://doi.org/10.1145/3240323.3240356" @default.
- W2892821876 hasPublicationYear "2018" @default.
- W2892821876 type Work @default.
- W2892821876 sameAs 2892821876 @default.
- W2892821876 citedByCount "58" @default.
- W2892821876 countsByYear W28928218762018 @default.
- W2892821876 countsByYear W28928218762019 @default.
- W2892821876 countsByYear W28928218762020 @default.
- W2892821876 countsByYear W28928218762021 @default.
- W2892821876 countsByYear W28928218762022 @default.
- W2892821876 countsByYear W28928218762023 @default.
- W2892821876 crossrefType "proceedings-article" @default.
- W2892821876 hasAuthorship W2892821876A5021827617 @default.
- W2892821876 hasAuthorship W2892821876A5052693492 @default.
- W2892821876 hasConcept C104317684 @default.
- W2892821876 hasConcept C105580179 @default.
- W2892821876 hasConcept C11413529 @default.
- W2892821876 hasConcept C149364088 @default.
- W2892821876 hasConcept C154945302 @default.
- W2892821876 hasConcept C185592680 @default.
- W2892821876 hasConcept C187834632 @default.
- W2892821876 hasConcept C203005215 @default.
- W2892821876 hasConcept C204321447 @default.
- W2892821876 hasConcept C41008148 @default.
- W2892821876 hasConcept C55493867 @default.
- W2892821876 hasConceptScore W2892821876C104317684 @default.
- W2892821876 hasConceptScore W2892821876C105580179 @default.
- W2892821876 hasConceptScore W2892821876C11413529 @default.
- W2892821876 hasConceptScore W2892821876C149364088 @default.
- W2892821876 hasConceptScore W2892821876C154945302 @default.
- W2892821876 hasConceptScore W2892821876C185592680 @default.
- W2892821876 hasConceptScore W2892821876C187834632 @default.
- W2892821876 hasConceptScore W2892821876C203005215 @default.
- W2892821876 hasConceptScore W2892821876C204321447 @default.
- W2892821876 hasConceptScore W2892821876C41008148 @default.
- W2892821876 hasConceptScore W2892821876C55493867 @default.
- W2892821876 hasLocation W28928218761 @default.
- W2892821876 hasOpenAccess W2892821876 @default.
- W2892821876 hasPrimaryLocation W28928218761 @default.
- W2892821876 hasRelatedWork W1484029852 @default.
- W2892821876 hasRelatedWork W1512718085 @default.
- W2892821876 hasRelatedWork W1544285860 @default.
- W2892821876 hasRelatedWork W1585034923 @default.
- W2892821876 hasRelatedWork W1592339875 @default.
- W2892821876 hasRelatedWork W1697423248 @default.
- W2892821876 hasRelatedWork W2435130738 @default.
- W2892821876 hasRelatedWork W3107474891 @default.
- W2892821876 hasRelatedWork W574870997 @default.
- W2892821876 hasRelatedWork W2610387714 @default.
- W2892821876 isParatext "false" @default.
- W2892821876 isRetracted "false" @default.
- W2892821876 magId "2892821876" @default.
- W2892821876 workType "article" @default.