Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149238099> ?p ?o ?g. }
- W3149238099 abstract "Implicit feedback is widely explored by modern recommender systems. Since the feedback is often sparse and imbalanced, it poses great challenges to the learning of complex interactions among users and items. Metric learning has been proposed to capture user-item interactions from implicit feedback, but existing methods only represent users and items in a single metric space, ignoring the fact that users can have multiple preferences and items can have multiple properties, which leads to potential conflicts limiting their performance in recommendation. To capture the multiple facets of user preferences and item properties while resolving their potential conflicts, we propose the novel framework of Multi-fAcet Recommender networks with Spherical optimization (MARS). By designing a cross-facet similarity measurement, we project users and items into multiple metric spaces for fine-grained representation learning, and compare them only in the proper spaces. Furthermore, we devise a spherical optimization strategy to enhance the effectiveness and robustness of the multi-facet recommendation framework. Extensive experiments on six real-world benchmark datasets show drastic performance gains brought by MARS, which constantly achieves up to 40% improvements over the state-of-the-art baselines regarding both HR and nDCG metrics." @default.
- W3149238099 created "2021-04-13" @default.
- W3149238099 creator A5006897094 @default.
- W3149238099 creator A5062694794 @default.
- W3149238099 creator A5074603286 @default.
- W3149238099 creator A5083137715 @default.
- W3149238099 creator A5091735030 @default.
- W3149238099 date "2021-03-27" @default.
- W3149238099 modified "2023-10-17" @default.
- W3149238099 title "Multi-Facet Recommender Networks with Spherical Optimization" @default.
- W3149238099 cites W1534477342 @default.
- W3149238099 cites W1551700376 @default.
- W3149238099 cites W1902027874 @default.
- W3149238099 cites W2059745395 @default.
- W3149238099 cites W2069870183 @default.
- W3149238099 cites W2090679992 @default.
- W3149238099 cites W2101409192 @default.
- W3149238099 cites W2102765684 @default.
- W3149238099 cites W2106053110 @default.
- W3149238099 cites W2140310134 @default.
- W3149238099 cites W2145001205 @default.
- W3149238099 cites W2152314154 @default.
- W3149238099 cites W2164019165 @default.
- W3149238099 cites W2283196293 @default.
- W3149238099 cites W2340502990 @default.
- W3149238099 cites W2468075526 @default.
- W3149238099 cites W2511131004 @default.
- W3149238099 cites W2565948352 @default.
- W3149238099 cites W2604397568 @default.
- W3149238099 cites W2604433096 @default.
- W3149238099 cites W2605350416 @default.
- W3149238099 cites W2734755249 @default.
- W3149238099 cites W2740920897 @default.
- W3149238099 cites W2743289629 @default.
- W3149238099 cites W2743969099 @default.
- W3149238099 cites W2757911951 @default.
- W3149238099 cites W2796238763 @default.
- W3149238099 cites W2798868970 @default.
- W3149238099 cites W2806321844 @default.
- W3149238099 cites W2809645418 @default.
- W3149238099 cites W2904683980 @default.
- W3149238099 cites W2906684937 @default.
- W3149238099 cites W2939052861 @default.
- W3149238099 cites W2943373497 @default.
- W3149238099 cites W2949599361 @default.
- W3149238099 cites W2963325056 @default.
- W3149238099 cites W2963655167 @default.
- W3149238099 cites W2964117810 @default.
- W3149238099 cites W2970427421 @default.
- W3149238099 cites W2971324494 @default.
- W3149238099 cites W2984006054 @default.
- W3149238099 cites W2997457842 @default.
- W3149238099 cites W2998128907 @default.
- W3149238099 cites W2998201756 @default.
- W3149238099 cites W3008625353 @default.
- W3149238099 cites W3022764178 @default.
- W3149238099 cites W3034339445 @default.
- W3149238099 cites W3081306295 @default.
- W3149238099 cites W3098649723 @default.
- W3149238099 cites W3100591234 @default.
- W3149238099 cites W3101397996 @default.
- W3149238099 cites W3102153333 @default.
- W3149238099 cites W3102317997 @default.
- W3149238099 cites W3102972033 @default.
- W3149238099 doi "https://doi.org/10.48550/arxiv.2103.14866" @default.
- W3149238099 hasPublicationYear "2021" @default.
- W3149238099 type Work @default.
- W3149238099 sameAs 3149238099 @default.
- W3149238099 citedByCount "1" @default.
- W3149238099 countsByYear W31492380992021 @default.
- W3149238099 crossrefType "posted-content" @default.
- W3149238099 hasAuthorship W3149238099A5006897094 @default.
- W3149238099 hasAuthorship W3149238099A5062694794 @default.
- W3149238099 hasAuthorship W3149238099A5074603286 @default.
- W3149238099 hasAuthorship W3149238099A5083137715 @default.
- W3149238099 hasAuthorship W3149238099A5091735030 @default.
- W3149238099 hasBestOaLocation W31492380991 @default.
- W3149238099 hasConcept C104317684 @default.
- W3149238099 hasConcept C119857082 @default.
- W3149238099 hasConcept C124101348 @default.
- W3149238099 hasConcept C127413603 @default.
- W3149238099 hasConcept C13280743 @default.
- W3149238099 hasConcept C154945302 @default.
- W3149238099 hasConcept C162324750 @default.
- W3149238099 hasConcept C176217482 @default.
- W3149238099 hasConcept C185592680 @default.
- W3149238099 hasConcept C185798385 @default.
- W3149238099 hasConcept C188198153 @default.
- W3149238099 hasConcept C189430467 @default.
- W3149238099 hasConcept C205649164 @default.
- W3149238099 hasConcept C21547014 @default.
- W3149238099 hasConcept C41008148 @default.
- W3149238099 hasConcept C55493867 @default.
- W3149238099 hasConcept C557471498 @default.
- W3149238099 hasConcept C63479239 @default.
- W3149238099 hasConcept C78519656 @default.
- W3149238099 hasConcept C86037889 @default.
- W3149238099 hasConceptScore W3149238099C104317684 @default.
- W3149238099 hasConceptScore W3149238099C119857082 @default.
- W3149238099 hasConceptScore W3149238099C124101348 @default.