Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386840045> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4386840045 abstract "Current recommender systems employ large-sized embedding tables with uniform dimensions for all features, leading to overfitting, high computational cost, and suboptimal generalizing performance. Many techniques aim to solve this issue by feature selection or embedding dimension search. However, these techniques typically select a fixed subset of features or embedding dimensions for all instances and feed all instances into one recommender model without considering heterogeneity between items or users. This paper proposes a novel instance-wise Hierarchical Architecture Search framework, iHAS, which automates neural architecture search at the instance level. Specifically, iHAS incorporates three stages: searching, clustering, and retraining. The searching stage identifies optimal instance-wise embedding dimensions across different field features via carefully designed Bernoulli gates with stochastic selection and regularizers. After obtaining these dimensions, the clustering stage divides samples into distinct groups via a deterministic selection approach of Bernoulli gates. The retraining stage then constructs different recommender models, each one designed with optimal dimensions for the corresponding group. We conduct extensive experiments to evaluate the proposed iHAS on two public benchmark datasets from a real-world recommender system. The experimental results demonstrate the effectiveness of iHAS and its outstanding transferability to widely-used deep recommendation models." @default.
- W4386840045 created "2023-09-19" @default.
- W4386840045 creator A5019118865 @default.
- W4386840045 creator A5020545071 @default.
- W4386840045 creator A5032424832 @default.
- W4386840045 creator A5040824128 @default.
- W4386840045 creator A5076381922 @default.
- W4386840045 date "2023-09-14" @default.
- W4386840045 modified "2023-09-27" @default.
- W4386840045 title "iHAS: Instance-wise Hierarchical Architecture Search for Deep Learning Recommendation Models" @default.
- W4386840045 doi "https://doi.org/10.48550/arxiv.2309.07967" @default.
- W4386840045 hasPublicationYear "2023" @default.
- W4386840045 type Work @default.
- W4386840045 citedByCount "0" @default.
- W4386840045 crossrefType "posted-content" @default.
- W4386840045 hasAuthorship W4386840045A5019118865 @default.
- W4386840045 hasAuthorship W4386840045A5020545071 @default.
- W4386840045 hasAuthorship W4386840045A5032424832 @default.
- W4386840045 hasAuthorship W4386840045A5040824128 @default.
- W4386840045 hasAuthorship W4386840045A5076381922 @default.
- W4386840045 hasBestOaLocation W43868400451 @default.
- W4386840045 hasConcept C119857082 @default.
- W4386840045 hasConcept C124101348 @default.
- W4386840045 hasConcept C13280743 @default.
- W4386840045 hasConcept C154945302 @default.
- W4386840045 hasConcept C185798385 @default.
- W4386840045 hasConcept C205649164 @default.
- W4386840045 hasConcept C21569690 @default.
- W4386840045 hasConcept C22019652 @default.
- W4386840045 hasConcept C41008148 @default.
- W4386840045 hasConcept C41608201 @default.
- W4386840045 hasConcept C50644808 @default.
- W4386840045 hasConcept C557471498 @default.
- W4386840045 hasConcept C73555534 @default.
- W4386840045 hasConcept C81917197 @default.
- W4386840045 hasConceptScore W4386840045C119857082 @default.
- W4386840045 hasConceptScore W4386840045C124101348 @default.
- W4386840045 hasConceptScore W4386840045C13280743 @default.
- W4386840045 hasConceptScore W4386840045C154945302 @default.
- W4386840045 hasConceptScore W4386840045C185798385 @default.
- W4386840045 hasConceptScore W4386840045C205649164 @default.
- W4386840045 hasConceptScore W4386840045C21569690 @default.
- W4386840045 hasConceptScore W4386840045C22019652 @default.
- W4386840045 hasConceptScore W4386840045C41008148 @default.
- W4386840045 hasConceptScore W4386840045C41608201 @default.
- W4386840045 hasConceptScore W4386840045C50644808 @default.
- W4386840045 hasConceptScore W4386840045C557471498 @default.
- W4386840045 hasConceptScore W4386840045C73555534 @default.
- W4386840045 hasConceptScore W4386840045C81917197 @default.
- W4386840045 hasLocation W43868400451 @default.
- W4386840045 hasOpenAccess W4386840045 @default.
- W4386840045 hasPrimaryLocation W43868400451 @default.
- W4386840045 hasRelatedWork W1773619406 @default.
- W4386840045 hasRelatedWork W2016738550 @default.
- W4386840045 hasRelatedWork W2075040002 @default.
- W4386840045 hasRelatedWork W2146781536 @default.
- W4386840045 hasRelatedWork W2348159088 @default.
- W4386840045 hasRelatedWork W2377968345 @default.
- W4386840045 hasRelatedWork W2391634835 @default.
- W4386840045 hasRelatedWork W2402445420 @default.
- W4386840045 hasRelatedWork W2989932438 @default.
- W4386840045 hasRelatedWork W3167191941 @default.
- W4386840045 isParatext "false" @default.
- W4386840045 isRetracted "false" @default.
- W4386840045 workType "article" @default.