Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308984522> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4308984522 endingPage "108442" @default.
- W4308984522 startingPage "108442" @default.
- W4308984522 abstract "Recommendation system is designed to tackle the information overload problem. The performance of a single recommendation system can be significantly improved if ensemble methods are used. In some recent works researchers seek ways to leverage past history for enhancing the performance of ensemble methods, The core concept rooted in this strand of research is based on exploiting user meta-data for enriching the input spaces for ensembler, however, in many user-agnostic recommendation scenarios such as ad-hoc searching where the user IDs and meta-data are absent, which makes such meta-data-driven ensembling method infeasible. In this work, we proposed a novel user-agnostic ensembling model Rec4Rec, which learns the representations of base recommenders from the input sequences via attention mechanism, in such a manner, the patterns and characteristics of input sequences are memorized within base recommender representations. The base recommender fitnesses are estimated through computing distance with input sequences and can be readily integrated with outputs of base recommenders for ensemble learning, no user-IDs or meta-data are required here as opposed to other meta-data-driven ensemble approaches. Experiment results show that Rec4Rec significantly outperforms the stacking ensembler. The embedding visualization proves that the proposed ensemble method can effectively distinguish the base recommenders. The superior performance of Rec4Rec demonstrates the importance of building representations for base recommenders of an ensemble in ad-hoc inquiries. • We embed both the item sequences and recommenders to estimate the fitness score. • Similar recommenders are close to each other in the embedding space. • Input item sequence is recommended to the best fit recommenders. • Comparing the embedding distance between input and recommenders to get the fitness scores." @default.
- W4308984522 created "2022-11-20" @default.
- W4308984522 creator A5006565014 @default.
- W4308984522 creator A5028873902 @default.
- W4308984522 creator A5044810272 @default.
- W4308984522 creator A5068325469 @default.
- W4308984522 date "2022-12-01" @default.
- W4308984522 modified "2023-09-27" @default.
- W4308984522 title "Enhancing recommender ensemble by estimating input fitness" @default.
- W4308984522 cites W1989977256 @default.
- W4308984522 cites W2040367556 @default.
- W4308984522 cites W2054141820 @default.
- W4308984522 cites W2137728971 @default.
- W4308984522 cites W2295739661 @default.
- W4308984522 cites W2783272285 @default.
- W4308984522 cites W2790360016 @default.
- W4308984522 cites W2902040508 @default.
- W4308984522 cites W2984100107 @default.
- W4308984522 cites W3012847895 @default.
- W4308984522 cites W3084247896 @default.
- W4308984522 cites W3088568480 @default.
- W4308984522 cites W4212883601 @default.
- W4308984522 doi "https://doi.org/10.1016/j.compeleceng.2022.108442" @default.
- W4308984522 hasPublicationYear "2022" @default.
- W4308984522 type Work @default.
- W4308984522 citedByCount "0" @default.
- W4308984522 crossrefType "journal-article" @default.
- W4308984522 hasAuthorship W4308984522A5006565014 @default.
- W4308984522 hasAuthorship W4308984522A5028873902 @default.
- W4308984522 hasAuthorship W4308984522A5044810272 @default.
- W4308984522 hasAuthorship W4308984522A5068325469 @default.
- W4308984522 hasConcept C119857082 @default.
- W4308984522 hasConcept C154945302 @default.
- W4308984522 hasConcept C41008148 @default.
- W4308984522 hasConcept C557471498 @default.
- W4308984522 hasConceptScore W4308984522C119857082 @default.
- W4308984522 hasConceptScore W4308984522C154945302 @default.
- W4308984522 hasConceptScore W4308984522C41008148 @default.
- W4308984522 hasConceptScore W4308984522C557471498 @default.
- W4308984522 hasLocation W43089845221 @default.
- W4308984522 hasOpenAccess W4308984522 @default.
- W4308984522 hasPrimaryLocation W43089845221 @default.
- W4308984522 hasRelatedWork W2045871438 @default.
- W4308984522 hasRelatedWork W2117346966 @default.
- W4308984522 hasRelatedWork W2316860054 @default.
- W4308984522 hasRelatedWork W2348159088 @default.
- W4308984522 hasRelatedWork W2369936857 @default.
- W4308984522 hasRelatedWork W2499363748 @default.
- W4308984522 hasRelatedWork W2525876841 @default.
- W4308984522 hasRelatedWork W2809363009 @default.
- W4308984522 hasRelatedWork W2883909875 @default.
- W4308984522 hasRelatedWork W2968745142 @default.
- W4308984522 hasVolume "104" @default.
- W4308984522 isParatext "false" @default.
- W4308984522 isRetracted "false" @default.
- W4308984522 workType "article" @default.