FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217803744> ?p ?o ?g. }

• W3217803744 abstract "CTR prediction is essential for modern recommender systems. Ranging from early factorization machines to deep learning based models in recent years, existing CTR methods focus on capturing useful feature interactions or mining important behavior patterns. Despite the effectiveness, we argue that these methods suffer from the risk of label sparsity (i.e., the user-item interactions are highly sparse with respect to the feature space), label noise (i.e., the collected user-item interactions are usually noisy), and the underuse of domain knowledge (i.e., the pairwise correlations between samples). To address these challenging problems, we propose a novel Multi-Interest Self-Supervised learning (MISS) framework which enhances the feature embeddings with interest-level self-supervision signals. With the help of two novel CNN-based multi-interest extractors,self-supervision signals are discovered with full considerations of different interest representations (point-wise and union-wise), interest dependencies (short-range and long-range), and interest correlations (inter-item and intra-item). Based on that, contrastive learning losses are further applied to the augmented views of interest representations, which effectively improves the feature representation learning. Furthermore, our proposed MISS framework can be used as an plug-in component with existing CTR prediction models and further boost their performances. Extensive experiments on three large-scale datasets show that MISS significantly outperforms the state-of-the-art models, by up to 13.55% in AUC, and also enjoys good compatibility with representative deep CTR models." @default.
• W3217803744 created "2021-12-06" @default.
• W3217803744 creator A5007730317 @default.
• W3217803744 creator A5019541869 @default.
• W3217803744 creator A5024235511 @default.
• W3217803744 creator A5054330014 @default.
• W3217803744 creator A5060200431 @default.
• W3217803744 creator A5065037360 @default.
• W3217803744 creator A5067483347 @default.
• W3217803744 creator A5076252609 @default.
• W3217803744 creator A5083350101 @default.
• W3217803744 date "2021-11-29" @default.
• W3217803744 modified "2023-10-16" @default.
• W3217803744 title "MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction" @default.
• W3217803744 cites W179875071 @default.
• W3217803744 cites W1964509623 @default.
• W3217803744 cites W2012905273 @default.
• W3217803744 cites W2064675550 @default.
• W3217803744 cites W2074694452 @default.
• W3217803744 cites W2143570267 @default.
• W3217803744 cites W2152790380 @default.
• W3217803744 cites W2157331557 @default.
• W3217803744 cites W2162979096 @default.
• W3217803744 cites W2163605009 @default.
• W3217803744 cites W2194775991 @default.
• W3217803744 cites W2295739661 @default.
• W3217803744 cites W2475334473 @default.
• W3217803744 cites W2723293840 @default.
• W3217803744 cites W2793768763 @default.
• W3217803744 cites W2842511635 @default.
• W3217803744 cites W2883725317 @default.
• W3217803744 cites W2887997457 @default.
• W3217803744 cites W2942947041 @default.
• W3217803744 cites W2951001079 @default.
• W3217803744 cites W2954817175 @default.
• W3217803744 cites W2962742544 @default.
• W3217803744 cites W2962745591 @default.
• W3217803744 cites W2963341956 @default.
• W3217803744 cites W2963403868 @default.
• W3217803744 cites W2963782635 @default.
• W3217803744 cites W2963924287 @default.
• W3217803744 cites W2964121744 @default.
• W3217803744 cites W2964182926 @default.
• W3217803744 cites W2964325980 @default.
• W3217803744 cites W2965373594 @default.
• W3217803744 cites W2979450518 @default.
• W3217803744 cites W2982902390 @default.
• W3217803744 cites W2984100107 @default.
• W3217803744 cites W2996428491 @default.
• W3217803744 cites W2997024057 @default.
• W3217803744 cites W3011411500 @default.
• W3217803744 cites W3034978746 @default.
• W3217803744 cites W3035524453 @default.
• W3217803744 cites W3080374445 @default.
• W3217803744 cites W3080642298 @default.
• W3217803744 cites W3081190557 @default.
• W3217803744 cites W3093519337 @default.
• W3217803744 cites W3093753441 @default.
• W3217803744 cites W3096591391 @default.
• W3217803744 cites W3100260481 @default.
• W3217803744 cites W3100859887 @default.
• W3217803744 cites W3101704389 @default.
• W3217803744 cites W3104506006 @default.
• W3217803744 cites W3105595718 @default.
• W3217803744 cites W3118062200 @default.
• W3217803744 cites W3135958856 @default.
• W3217803744 cites W3141023492 @default.
• W3217803744 cites W3153325943 @default.
• W3217803744 cites W3153687269 @default.
• W3217803744 cites W3167730891 @default.
• W3217803744 cites W3190524507 @default.
• W3217803744 cites W3208709726 @default.
• W3217803744 doi "https://doi.org/10.48550/arxiv.2111.15068" @default.
• W3217803744 hasPublicationYear "2021" @default.
• W3217803744 type Work @default.
• W3217803744 sameAs 3217803744 @default.
• W3217803744 citedByCount "0" @default.
• W3217803744 crossrefType "posted-content" @default.
• W3217803744 hasAuthorship W3217803744A5007730317 @default.
• W3217803744 hasAuthorship W3217803744A5019541869 @default.
• W3217803744 hasAuthorship W3217803744A5024235511 @default.
• W3217803744 hasAuthorship W3217803744A5054330014 @default.
• W3217803744 hasAuthorship W3217803744A5060200431 @default.
• W3217803744 hasAuthorship W3217803744A5065037360 @default.
• W3217803744 hasAuthorship W3217803744A5067483347 @default.
• W3217803744 hasAuthorship W3217803744A5076252609 @default.
• W3217803744 hasAuthorship W3217803744A5083350101 @default.
• W3217803744 hasBestOaLocation W32178037441 @default.
• W3217803744 hasConcept C108583219 @default.
• W3217803744 hasConcept C119857082 @default.
• W3217803744 hasConcept C124101348 @default.
• W3217803744 hasConcept C138885662 @default.
• W3217803744 hasConcept C154945302 @default.
• W3217803744 hasConcept C184898388 @default.
• W3217803744 hasConcept C2776401178 @default.
• W3217803744 hasConcept C41008148 @default.
• W3217803744 hasConcept C41895202 @default.
• W3217803744 hasConcept C557471498 @default.
• W3217803744 hasConcept C59404180 @default.
• W3217803744 hasConceptScore W3217803744C108583219 @default.

• next