Matches in SemOpenAlex for { <https://semopenalex.org/work/W3183450131> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3183450131 abstract "Click-through rate (CTR) prediction plays important role in personalized advertising and recommender systems. Though many models have been proposed such as FM, FFM and DeepFM in recent years, feature engineering is still a very important way to improve the model performance in many applications because using raw features can rarely lead to optimal results. For example, the continuous features are usually transformed to the power forms by adding a new feature to allow it to easily form non-linear functions of the feature. However, this kind of feature engineering heavily relies on peoples experience and it is both time consuming and labor consuming. On the other side, concise CTR model with both fast online serving speed and good model performance is critical for many real life applications. In this paper, we propose LeafFM model based on FM to generate new features from the original feature embedding by learning the transformation functions automatically. We also design three concrete Leaf-FM models according to the different strategies of combing the original and the generated features. Extensive experiments are conducted on three real-world datasets and the results show Leaf-FM model outperforms standard FMs by a large margin. Compared with FFMs, Leaf-FM can achieve significantly better performance with much less parameters. In Avazu and Malware dataset, add version Leaf-FM achieves comparable performance with some deep learning based models such as DNN and AutoInt. As an improved FM model, Leaf-FM has the same computation complexity with FM in online serving phase and it means Leaf-FM is applicable in many industry applications because of its better performance and high computation efficiency." @default.
- W3183450131 created "2021-08-02" @default.
- W3183450131 creator A5004628587 @default.
- W3183450131 creator A5058668034 @default.
- W3183450131 creator A5073720889 @default.
- W3183450131 date "2021-07-26" @default.
- W3183450131 modified "2023-10-16" @default.
- W3183450131 title "Leaf-FM: A Learnable Feature Generation Factorization Machine for Click-Through Rate Prediction." @default.
- W3183450131 cites W2054141820 @default.
- W3183450131 cites W2055079831 @default.
- W3183450131 cites W2074694452 @default.
- W3183450131 cites W2076618162 @default.
- W3183450131 cites W2139750075 @default.
- W3183450131 cites W2162979096 @default.
- W3183450131 cites W2295739661 @default.
- W3183450131 cites W2443960221 @default.
- W3183450131 cites W2475334473 @default.
- W3183450131 cites W2512971201 @default.
- W3183450131 cites W2548570154 @default.
- W3183450131 cites W2947737663 @default.
- W3183450131 cites W2949117887 @default.
- W3183450131 cites W2951001079 @default.
- W3183450131 cites W2964052347 @default.
- W3183450131 cites W2964182926 @default.
- W3183450131 cites W3016842236 @default.
- W3183450131 cites W3098723082 @default.
- W3183450131 cites W3104789011 @default.
- W3183450131 hasPublicationYear "2021" @default.
- W3183450131 type Work @default.
- W3183450131 sameAs 3183450131 @default.
- W3183450131 citedByCount "0" @default.
- W3183450131 crossrefType "posted-content" @default.
- W3183450131 hasAuthorship W3183450131A5004628587 @default.
- W3183450131 hasAuthorship W3183450131A5058668034 @default.
- W3183450131 hasAuthorship W3183450131A5073720889 @default.
- W3183450131 hasConcept C108583219 @default.
- W3183450131 hasConcept C11413529 @default.
- W3183450131 hasConcept C115174607 @default.
- W3183450131 hasConcept C119857082 @default.
- W3183450131 hasConcept C138885662 @default.
- W3183450131 hasConcept C154945302 @default.
- W3183450131 hasConcept C23123220 @default.
- W3183450131 hasConcept C2776401178 @default.
- W3183450131 hasConcept C2778827112 @default.
- W3183450131 hasConcept C41008148 @default.
- W3183450131 hasConcept C41608201 @default.
- W3183450131 hasConcept C41895202 @default.
- W3183450131 hasConcept C45374587 @default.
- W3183450131 hasConcept C774472 @default.
- W3183450131 hasConceptScore W3183450131C108583219 @default.
- W3183450131 hasConceptScore W3183450131C11413529 @default.
- W3183450131 hasConceptScore W3183450131C115174607 @default.
- W3183450131 hasConceptScore W3183450131C119857082 @default.
- W3183450131 hasConceptScore W3183450131C138885662 @default.
- W3183450131 hasConceptScore W3183450131C154945302 @default.
- W3183450131 hasConceptScore W3183450131C23123220 @default.
- W3183450131 hasConceptScore W3183450131C2776401178 @default.
- W3183450131 hasConceptScore W3183450131C2778827112 @default.
- W3183450131 hasConceptScore W3183450131C41008148 @default.
- W3183450131 hasConceptScore W3183450131C41608201 @default.
- W3183450131 hasConceptScore W3183450131C41895202 @default.
- W3183450131 hasConceptScore W3183450131C45374587 @default.
- W3183450131 hasConceptScore W3183450131C774472 @default.
- W3183450131 hasLocation W31834501311 @default.
- W3183450131 hasOpenAccess W3183450131 @default.
- W3183450131 hasPrimaryLocation W31834501311 @default.
- W3183450131 hasRelatedWork W1671907758 @default.
- W3183450131 hasRelatedWork W1977640460 @default.
- W3183450131 hasRelatedWork W2108599331 @default.
- W3183450131 hasRelatedWork W2124689713 @default.
- W3183450131 hasRelatedWork W2538294494 @default.
- W3183450131 hasRelatedWork W2599654091 @default.
- W3183450131 hasRelatedWork W2789660531 @default.
- W3183450131 hasRelatedWork W2797938346 @default.
- W3183450131 hasRelatedWork W2887424665 @default.
- W3183450131 hasRelatedWork W2896688807 @default.
- W3183450131 hasRelatedWork W2912081564 @default.
- W3183450131 hasRelatedWork W2913856343 @default.
- W3183450131 hasRelatedWork W2949207836 @default.
- W3183450131 hasRelatedWork W2996964951 @default.
- W3183450131 hasRelatedWork W3000173096 @default.
- W3183450131 hasRelatedWork W3043907666 @default.
- W3183450131 hasRelatedWork W3105024967 @default.
- W3183450131 hasRelatedWork W3162861012 @default.
- W3183450131 hasRelatedWork W3202501261 @default.
- W3183450131 hasRelatedWork W2946368286 @default.
- W3183450131 isParatext "false" @default.
- W3183450131 isRetracted "false" @default.
- W3183450131 magId "3183450131" @default.
- W3183450131 workType "article" @default.