Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319792005> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4319792005 abstract "Recommender systems usually rely on observed user interaction data to build personalized recommendation models, assuming that the observed data reflect user interest. However, user interacting with an item may also due to conformity, the need to follow popular items. Most previous studies neglect user's conformity and entangle interest with it, which may cause the recommender systems fail to provide satisfying results. Therefore, from the cause-effect view, disentangling these interaction causes is a crucial issue. It also contributes to OOD problems, where training and test data are out-of-distribution. Nevertheless, it is quite challenging as we lack the signal to differentiate interest and conformity. The data sparsity of pure cause and the items' long-tail problem hinder disentangled causal embedding. In this paper, we propose DCCL, a framework that adopts contrastive learning to disentangle these two causes by sample augmentation for interest and conformity respectively. Futhermore, DCCL is model-agnostic, which can be easily deployed in any industrial online system. Extensive experiments are conducted over two real-world datasets and DCCL outperforms state-of-the-art baselines on top of various backbone models in various OOD environments. We also demonstrate the performance improvements by online A/B testing on Kuaishou, a billion-user scale short-video recommender system." @default.
- W4319792005 created "2023-02-11" @default.
- W4319792005 creator A5011688144 @default.
- W4319792005 creator A5028462736 @default.
- W4319792005 creator A5056383196 @default.
- W4319792005 creator A5057350256 @default.
- W4319792005 creator A5060052615 @default.
- W4319792005 creator A5062939922 @default.
- W4319792005 creator A5069585633 @default.
- W4319792005 creator A5089453138 @default.
- W4319792005 date "2023-02-06" @default.
- W4319792005 modified "2023-10-18" @default.
- W4319792005 title "Disentangled Causal Embedding With Contrastive Learning For Recommender System" @default.
- W4319792005 doi "https://doi.org/10.48550/arxiv.2302.03248" @default.
- W4319792005 hasPublicationYear "2023" @default.
- W4319792005 type Work @default.
- W4319792005 citedByCount "0" @default.
- W4319792005 crossrefType "posted-content" @default.
- W4319792005 hasAuthorship W4319792005A5011688144 @default.
- W4319792005 hasAuthorship W4319792005A5028462736 @default.
- W4319792005 hasAuthorship W4319792005A5056383196 @default.
- W4319792005 hasAuthorship W4319792005A5057350256 @default.
- W4319792005 hasAuthorship W4319792005A5060052615 @default.
- W4319792005 hasAuthorship W4319792005A5062939922 @default.
- W4319792005 hasAuthorship W4319792005A5069585633 @default.
- W4319792005 hasAuthorship W4319792005A5089453138 @default.
- W4319792005 hasBestOaLocation W43197920051 @default.
- W4319792005 hasConcept C119857082 @default.
- W4319792005 hasConcept C142172996 @default.
- W4319792005 hasConcept C154945302 @default.
- W4319792005 hasConcept C15744967 @default.
- W4319792005 hasConcept C185592680 @default.
- W4319792005 hasConcept C198531522 @default.
- W4319792005 hasConcept C23123220 @default.
- W4319792005 hasConcept C41008148 @default.
- W4319792005 hasConcept C41608201 @default.
- W4319792005 hasConcept C43617362 @default.
- W4319792005 hasConcept C557471498 @default.
- W4319792005 hasConcept C77805123 @default.
- W4319792005 hasConceptScore W4319792005C119857082 @default.
- W4319792005 hasConceptScore W4319792005C142172996 @default.
- W4319792005 hasConceptScore W4319792005C154945302 @default.
- W4319792005 hasConceptScore W4319792005C15744967 @default.
- W4319792005 hasConceptScore W4319792005C185592680 @default.
- W4319792005 hasConceptScore W4319792005C198531522 @default.
- W4319792005 hasConceptScore W4319792005C23123220 @default.
- W4319792005 hasConceptScore W4319792005C41008148 @default.
- W4319792005 hasConceptScore W4319792005C41608201 @default.
- W4319792005 hasConceptScore W4319792005C43617362 @default.
- W4319792005 hasConceptScore W4319792005C557471498 @default.
- W4319792005 hasConceptScore W4319792005C77805123 @default.
- W4319792005 hasLocation W43197920051 @default.
- W4319792005 hasOpenAccess W4319792005 @default.
- W4319792005 hasPrimaryLocation W43197920051 @default.
- W4319792005 hasRelatedWork W2117346966 @default.
- W4319792005 hasRelatedWork W2348159088 @default.
- W4319792005 hasRelatedWork W2350747448 @default.
- W4319792005 hasRelatedWork W2368095327 @default.
- W4319792005 hasRelatedWork W2369936857 @default.
- W4319792005 hasRelatedWork W2499363748 @default.
- W4319792005 hasRelatedWork W2809363009 @default.
- W4319792005 hasRelatedWork W2883909875 @default.
- W4319792005 hasRelatedWork W2968745142 @default.
- W4319792005 hasRelatedWork W4289860834 @default.
- W4319792005 isParatext "false" @default.
- W4319792005 isRetracted "false" @default.
- W4319792005 workType "article" @default.