Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298148912> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4298148912 endingPage "118931" @default.
- W4298148912 startingPage "118931" @default.
- W4298148912 abstract "Semi-supervised learning (SSL) has drawn much attention since it can alleviate the predicament in which only limited labels can be accessed, with the help of numerous unlabeled data. Many deep neural networks (NNs) based SSL methods have been proposed recently, which mostly focus on image classification tasks, while fewer efforts have been taken to tabular data related regression scenarios. In this paper, to handle the semi-supervised regression problem for tabular data with NNs based methods, we empirically observe the demerits of previous methods and present a novel framework, to explore the combination of self teaching and mutual teaching. For one thing, self teaching is employed to each base learner by using consistency regularization so that the model is driven to be more stable and also robust to local perturbations. For another, the knowledge of other base learners is extracted and filtered to perform mutual teaching to avoid the confirmation bias problem and boost the training of each base learner. Here, we employ an uncertainty-based strategy for the filtering of knowledge in mutual teaching. Extensive experiments are performed on multiple real-world datasets to demonstrate the effectiveness of previous methods and the proposed framework, and further analyses are conducted to understand the influence of each factor in the proposed framework." @default.
- W4298148912 created "2022-10-01" @default.
- W4298148912 creator A5010357285 @default.
- W4298148912 creator A5068305259 @default.
- W4298148912 creator A5070623811 @default.
- W4298148912 creator A5075729645 @default.
- W4298148912 date "2023-03-01" @default.
- W4298148912 modified "2023-10-15" @default.
- W4298148912 title "Exploring the combination of self and mutual teaching for tabular-data-related semi-supervised regression" @default.
- W4298148912 cites W2048679005 @default.
- W4298148912 cites W2048871128 @default.
- W4298148912 cites W2085443648 @default.
- W4298148912 cites W2097089247 @default.
- W4298148912 cites W2133556223 @default.
- W4298148912 cites W2145376937 @default.
- W4298148912 cites W2808139377 @default.
- W4298148912 cites W2889213362 @default.
- W4298148912 cites W2919115771 @default.
- W4298148912 cites W2964159205 @default.
- W4298148912 cites W2984353870 @default.
- W4298148912 cites W3009186105 @default.
- W4298148912 doi "https://doi.org/10.1016/j.eswa.2022.118931" @default.
- W4298148912 hasPublicationYear "2023" @default.
- W4298148912 type Work @default.
- W4298148912 citedByCount "1" @default.
- W4298148912 crossrefType "journal-article" @default.
- W4298148912 hasAuthorship W4298148912A5010357285 @default.
- W4298148912 hasAuthorship W4298148912A5068305259 @default.
- W4298148912 hasAuthorship W4298148912A5070623811 @default.
- W4298148912 hasAuthorship W4298148912A5075729645 @default.
- W4298148912 hasConcept C105795698 @default.
- W4298148912 hasConcept C119857082 @default.
- W4298148912 hasConcept C124101348 @default.
- W4298148912 hasConcept C152139883 @default.
- W4298148912 hasConcept C154945302 @default.
- W4298148912 hasConcept C2776135515 @default.
- W4298148912 hasConcept C2776436953 @default.
- W4298148912 hasConcept C33923547 @default.
- W4298148912 hasConcept C41008148 @default.
- W4298148912 hasConcept C50644808 @default.
- W4298148912 hasConcept C83546350 @default.
- W4298148912 hasConceptScore W4298148912C105795698 @default.
- W4298148912 hasConceptScore W4298148912C119857082 @default.
- W4298148912 hasConceptScore W4298148912C124101348 @default.
- W4298148912 hasConceptScore W4298148912C152139883 @default.
- W4298148912 hasConceptScore W4298148912C154945302 @default.
- W4298148912 hasConceptScore W4298148912C2776135515 @default.
- W4298148912 hasConceptScore W4298148912C2776436953 @default.
- W4298148912 hasConceptScore W4298148912C33923547 @default.
- W4298148912 hasConceptScore W4298148912C41008148 @default.
- W4298148912 hasConceptScore W4298148912C50644808 @default.
- W4298148912 hasConceptScore W4298148912C83546350 @default.
- W4298148912 hasLocation W42981489121 @default.
- W4298148912 hasOpenAccess W4298148912 @default.
- W4298148912 hasPrimaryLocation W42981489121 @default.
- W4298148912 hasRelatedWork W1970834875 @default.
- W4298148912 hasRelatedWork W1977605874 @default.
- W4298148912 hasRelatedWork W2000517284 @default.
- W4298148912 hasRelatedWork W2136503713 @default.
- W4298148912 hasRelatedWork W2363755581 @default.
- W4298148912 hasRelatedWork W2365318811 @default.
- W4298148912 hasRelatedWork W2375330620 @default.
- W4298148912 hasRelatedWork W2378091429 @default.
- W4298148912 hasRelatedWork W2466816617 @default.
- W4298148912 hasRelatedWork W3174028392 @default.
- W4298148912 hasVolume "213" @default.
- W4298148912 isParatext "false" @default.
- W4298148912 isRetracted "false" @default.
- W4298148912 workType "article" @default.