Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216272927> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3216272927 endingPage "108474" @default.
- W3216272927 startingPage "108474" @default.
- W3216272927 abstract "Existing works on Automated Machine Learning (AutoML) are mainly based on predefined search space. This paper seeks synergetic automation of two ingredients, i.e., search space and search strategies. Specifically, we formulate the automation of search space and search strategies as a combinatorial optimization problem. Our empirical study on many architecture benchmarks shows that identifying the suitable search space exerts more effect than choosing a sophisticated search strategy. Motivated by this, we attempt to leverage a machine learning method to solve the discrete optimization problem, and thus develop a Layered Architecture Search Tree (LArST) approach to synergize these two components. In addition, we use a probe model-based method to extract dataset-wise features, i.e., meta-features, which is able to facilitate the estimation of proper search space and search strategy for a given task. Experimental results show the efficacy of our approach under different search mechanisms and various datasets and hardware platforms." @default.
- W3216272927 created "2021-12-06" @default.
- W3216272927 creator A5019539636 @default.
- W3216272927 creator A5027039492 @default.
- W3216272927 creator A5048141765 @default.
- W3216272927 creator A5054079327 @default.
- W3216272927 date "2022-04-01" @default.
- W3216272927 modified "2023-09-25" @default.
- W3216272927 title "Automated search space and search strategy selection for AutoML" @default.
- W3216272927 cites W2001389398 @default.
- W3216272927 cites W2089213632 @default.
- W3216272927 cites W2112796928 @default.
- W3216272927 cites W2167467747 @default.
- W3216272927 cites W2963912358 @default.
- W3216272927 cites W3137013162 @default.
- W3216272927 cites W3162847008 @default.
- W3216272927 cites W3184418149 @default.
- W3216272927 doi "https://doi.org/10.1016/j.patcog.2021.108474" @default.
- W3216272927 hasPublicationYear "2022" @default.
- W3216272927 type Work @default.
- W3216272927 sameAs 3216272927 @default.
- W3216272927 citedByCount "4" @default.
- W3216272927 countsByYear W32162729272022 @default.
- W3216272927 countsByYear W32162729272023 @default.
- W3216272927 crossrefType "journal-article" @default.
- W3216272927 hasAuthorship W3216272927A5019539636 @default.
- W3216272927 hasAuthorship W3216272927A5027039492 @default.
- W3216272927 hasAuthorship W3216272927A5048141765 @default.
- W3216272927 hasAuthorship W3216272927A5054079327 @default.
- W3216272927 hasConcept C111919701 @default.
- W3216272927 hasConcept C11413529 @default.
- W3216272927 hasConcept C115901376 @default.
- W3216272927 hasConcept C119857082 @default.
- W3216272927 hasConcept C124101348 @default.
- W3216272927 hasConcept C125583679 @default.
- W3216272927 hasConcept C127413603 @default.
- W3216272927 hasConcept C139979381 @default.
- W3216272927 hasConcept C14362708 @default.
- W3216272927 hasConcept C153083717 @default.
- W3216272927 hasConcept C154945302 @default.
- W3216272927 hasConcept C19889080 @default.
- W3216272927 hasConcept C201789804 @default.
- W3216272927 hasConcept C203208320 @default.
- W3216272927 hasConcept C2778572836 @default.
- W3216272927 hasConcept C41008148 @default.
- W3216272927 hasConcept C78519656 @default.
- W3216272927 hasConceptScore W3216272927C111919701 @default.
- W3216272927 hasConceptScore W3216272927C11413529 @default.
- W3216272927 hasConceptScore W3216272927C115901376 @default.
- W3216272927 hasConceptScore W3216272927C119857082 @default.
- W3216272927 hasConceptScore W3216272927C124101348 @default.
- W3216272927 hasConceptScore W3216272927C125583679 @default.
- W3216272927 hasConceptScore W3216272927C127413603 @default.
- W3216272927 hasConceptScore W3216272927C139979381 @default.
- W3216272927 hasConceptScore W3216272927C14362708 @default.
- W3216272927 hasConceptScore W3216272927C153083717 @default.
- W3216272927 hasConceptScore W3216272927C154945302 @default.
- W3216272927 hasConceptScore W3216272927C19889080 @default.
- W3216272927 hasConceptScore W3216272927C201789804 @default.
- W3216272927 hasConceptScore W3216272927C203208320 @default.
- W3216272927 hasConceptScore W3216272927C2778572836 @default.
- W3216272927 hasConceptScore W3216272927C41008148 @default.
- W3216272927 hasConceptScore W3216272927C78519656 @default.
- W3216272927 hasLocation W32162729271 @default.
- W3216272927 hasOpenAccess W3216272927 @default.
- W3216272927 hasPrimaryLocation W32162729271 @default.
- W3216272927 hasRelatedWork W1644411414 @default.
- W3216272927 hasRelatedWork W2064794194 @default.
- W3216272927 hasRelatedWork W2125033394 @default.
- W3216272927 hasRelatedWork W2159879965 @default.
- W3216272927 hasRelatedWork W2354057059 @default.
- W3216272927 hasRelatedWork W2593395660 @default.
- W3216272927 hasRelatedWork W2808808802 @default.
- W3216272927 hasRelatedWork W3014882394 @default.
- W3216272927 hasRelatedWork W3106196307 @default.
- W3216272927 hasRelatedWork W2998661990 @default.
- W3216272927 hasVolume "124" @default.
- W3216272927 isParatext "false" @default.
- W3216272927 isRetracted "false" @default.
- W3216272927 magId "3216272927" @default.
- W3216272927 workType "article" @default.