FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2810631159> ?p ?o ?g. }

• W2810631159 abstract "User response prediction is a crucial component for personalized information retrieval and filtering scenarios, such as recommender system and web search. The data in user response prediction is mostly in a multi-field categorical format and transformed into sparse representations via one-hot encoding. Due to the sparsity problems in representation and optimization, most research focuses on feature engineering and shallow modeling. Recently, deep neural networks have attracted research attention on such a problem for their high capacity and end-to-end training scheme. In this paper, we study user response prediction in the scenario of click prediction. We first analyze a coupled gradient issue in latent vector-based models and propose kernel product to learn field-aware feature interactions. Then we discuss an insensitive gradient issue in DNN-based models and propose Product-based Neural Network (PNN) which adopts a feature extractor to explore feature interactions. Generalizing the kernel product to a net-in-net architecture, we further propose Product-network In Network (PIN) which can generalize previous models. Extensive experiments on 4 industrial datasets and 1 contest dataset demonstrate that our models consistently outperform 8 baselines on both AUC and log loss. Besides, PIN makes great CTR improvement (relatively 34.67%) in online A/B test." @default.
• W2810631159 created "2018-07-10" @default.
• W2810631159 creator A5001571390 @default.
• W2810631159 creator A5019541869 @default.
• W2810631159 creator A5037311972 @default.
• W2810631159 creator A5047927529 @default.
• W2810631159 creator A5054330014 @default.
• W2810631159 creator A5083350101 @default.
• W2810631159 creator A5090720315 @default.
• W2810631159 creator A5091740494 @default.
• W2810631159 date "2018-07-01" @default.
• W2810631159 modified "2023-09-27" @default.
• W2810631159 title "Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data" @default.
• W2810631159 cites W1522301498 @default.
• W2810631159 cites W1533861849 @default.
• W2810631159 cites W1799366690 @default.
• W2810631159 cites W1833977909 @default.
• W2810631159 cites W1969675113 @default.
• W2810631159 cites W1983548143 @default.
• W2810631159 cites W2012905273 @default.
• W2810631159 cites W2018049374 @default.
• W2810631159 cites W2031002853 @default.
• W2810631159 cites W2039842578 @default.
• W2810631159 cites W2054141820 @default.
• W2810631159 cites W2074694452 @default.
• W2810631159 cites W2076618162 @default.
• W2810631159 cites W2090883204 @default.
• W2810631159 cites W2097117768 @default.
• W2810631159 cites W2099213975 @default.
• W2810631159 cites W2099391294 @default.
• W2810631159 cites W2129235726 @default.
• W2810631159 cites W2146502635 @default.
• W2810631159 cites W2149822245 @default.
• W2810631159 cites W2157881433 @default.
• W2810631159 cites W2162979096 @default.
• W2810631159 cites W2211399443 @default.
• W2810631159 cites W2284050935 @default.
• W2810631159 cites W2295739661 @default.
• W2810631159 cites W2509235963 @default.
• W2810631159 cites W2512971201 @default.
• W2810631159 cites W2517540742 @default.
• W2810631159 cites W2534189265 @default.
• W2810631159 cites W2548570154 @default.
• W2810631159 cites W2557283755 @default.
• W2810631159 cites W2583200575 @default.
• W2810631159 cites W2623127191 @default.
• W2810631159 cites W2739273093 @default.
• W2810631159 cites W2740885325 @default.
• W2810631159 cites W2743904806 @default.
• W2810631159 cites W2744939564 @default.
• W2810631159 cites W2949117887 @default.
• W2810631159 cites W2949274928 @default.
• W2810631159 cites W2950178297 @default.
• W2810631159 cites W2951001079 @default.
• W2810631159 cites W2951581544 @default.
• W2810631159 cites W2951707557 @default.
• W2810631159 cites W2963323306 @default.
• W2810631159 cites W2964325980 @default.
• W2810631159 cites W3102476541 @default.
• W2810631159 cites W3146803896 @default.
• W2810631159 doi "https://doi.org/10.48550/arxiv.1807.00311" @default.
• W2810631159 hasPublicationYear "2018" @default.
• W2810631159 type Work @default.
• W2810631159 sameAs 2810631159 @default.
• W2810631159 citedByCount "2" @default.
• W2810631159 countsByYear W28106311592019 @default.
• W2810631159 countsByYear W28106311592021 @default.
• W2810631159 crossrefType "posted-content" @default.
• W2810631159 hasAuthorship W2810631159A5001571390 @default.
• W2810631159 hasAuthorship W2810631159A5019541869 @default.
• W2810631159 hasAuthorship W2810631159A5037311972 @default.
• W2810631159 hasAuthorship W2810631159A5047927529 @default.
• W2810631159 hasAuthorship W2810631159A5054330014 @default.
• W2810631159 hasAuthorship W2810631159A5083350101 @default.
• W2810631159 hasAuthorship W2810631159A5090720315 @default.
• W2810631159 hasAuthorship W2810631159A5091740494 @default.
• W2810631159 hasBestOaLocation W28106311591 @default.
• W2810631159 hasConcept C108583219 @default.
• W2810631159 hasConcept C114614502 @default.
• W2810631159 hasConcept C119857082 @default.
• W2810631159 hasConcept C124101348 @default.
• W2810631159 hasConcept C138885662 @default.
• W2810631159 hasConcept C154945302 @default.
• W2810631159 hasConcept C202444582 @default.
• W2810631159 hasConcept C2524010 @default.
• W2810631159 hasConcept C2776401178 @default.
• W2810631159 hasConcept C2778827112 @default.
• W2810631159 hasConcept C32900221 @default.
• W2810631159 hasConcept C33923547 @default.
• W2810631159 hasConcept C41008148 @default.
• W2810631159 hasConcept C41895202 @default.
• W2810631159 hasConcept C50644808 @default.
• W2810631159 hasConcept C5274069 @default.
• W2810631159 hasConcept C74193536 @default.
• W2810631159 hasConcept C90673727 @default.
• W2810631159 hasConcept C9652623 @default.
• W2810631159 hasConceptScore W2810631159C108583219 @default.
• W2810631159 hasConceptScore W2810631159C114614502 @default.
• W2810631159 hasConceptScore W2810631159C119857082 @default.
• W2810631159 hasConceptScore W2810631159C124101348 @default.

• next