Matches in SemOpenAlex for { <https://semopenalex.org/work/W2978161329> ?p ?o ?g. }
- W2978161329 abstract "Active Learning (AL) is a machine learning framework that aims to efficiently select a limited labeled data to construct an effective model given huge amount of unlabeled data on the side. Most studies in AL focus on how to select the unlabeled data to be labeled by a human oracle in order to maximize the performance gain of the model with as little labeling effort as possible. In this work, however, we focus not only on how to select appropriate data instances but also how to select informative features, more specifically, categorical features to be labeled by the oracle in a unified manner. The unification means that we select the best choice of item to label where the item can be either a feature or an instance on each iteration given a unified scoring function to make the decision. The method that we propose is by synthesizing new instances that represent a set of features. By utilizing synthesized instances, we can treat this set of features as if they are regular instances. Therefore they could be compared on an equal ground when the model tries to select which instances to be labeled by the oracle. The features used to build the synthesized instances need to be carefully selected so the resulting synthesized instances could improve the model and not introducing any contradicting information. We utilize hierarchical clustering in order to group features that own similar content. This is done first by picking clusters whose label purity are estimated to be high. Then we score a feature based on how common the feature is in the cluster and how related the feature is to the estimated majority label. The top scoring features will then be used to synthesize instances. We demonstrate the effectiveness of the proposed method through a few data sets that consist of only categorical features where the feature labeling makes more sense to labeling oracles. The experiment results show that adopting the unified approach creates clear benefit to model construction, especially in the early stage where we can efficiently obtain an effective model through only a few iterations, compared to the one using only instance labeling for model construction." @default.
- W2978161329 created "2019-10-10" @default.
- W2978161329 creator A5026523368 @default.
- W2978161329 creator A5030897009 @default.
- W2978161329 creator A5038395989 @default.
- W2978161329 date "2019-07-01" @default.
- W2978161329 modified "2023-09-28" @default.
- W2978161329 title "A Unified Approach on Active Learning Dual Supervision" @default.
- W2978161329 cites W1531719573 @default.
- W2978161329 cites W1599454686 @default.
- W2978161329 cites W1924689489 @default.
- W2978161329 cites W2042932437 @default.
- W2978161329 cites W2054034748 @default.
- W2978161329 cites W2109378394 @default.
- W2978161329 cites W2159681823 @default.
- W2978161329 cites W2165968176 @default.
- W2978161329 cites W2166353350 @default.
- W2978161329 cites W2903158431 @default.
- W2978161329 cites W3120740533 @default.
- W2978161329 doi "https://doi.org/10.1109/ijcnn.2019.8851706" @default.
- W2978161329 hasPublicationYear "2019" @default.
- W2978161329 type Work @default.
- W2978161329 sameAs 2978161329 @default.
- W2978161329 citedByCount "1" @default.
- W2978161329 countsByYear W29781613292021 @default.
- W2978161329 crossrefType "proceedings-article" @default.
- W2978161329 hasAuthorship W2978161329A5026523368 @default.
- W2978161329 hasAuthorship W2978161329A5030897009 @default.
- W2978161329 hasAuthorship W2978161329A5038395989 @default.
- W2978161329 hasConcept C115903868 @default.
- W2978161329 hasConcept C119857082 @default.
- W2978161329 hasConcept C120665830 @default.
- W2978161329 hasConcept C121332964 @default.
- W2978161329 hasConcept C124101348 @default.
- W2978161329 hasConcept C124952713 @default.
- W2978161329 hasConcept C138885662 @default.
- W2978161329 hasConcept C142362112 @default.
- W2978161329 hasConcept C154945302 @default.
- W2978161329 hasConcept C177264268 @default.
- W2978161329 hasConcept C192209626 @default.
- W2978161329 hasConcept C199360897 @default.
- W2978161329 hasConcept C2776145971 @default.
- W2978161329 hasConcept C2776401178 @default.
- W2978161329 hasConcept C2780801425 @default.
- W2978161329 hasConcept C2780980858 @default.
- W2978161329 hasConcept C41008148 @default.
- W2978161329 hasConcept C41895202 @default.
- W2978161329 hasConcept C5274069 @default.
- W2978161329 hasConcept C55166926 @default.
- W2978161329 hasConcept C73555534 @default.
- W2978161329 hasConcept C94124525 @default.
- W2978161329 hasConcept C96146094 @default.
- W2978161329 hasConceptScore W2978161329C115903868 @default.
- W2978161329 hasConceptScore W2978161329C119857082 @default.
- W2978161329 hasConceptScore W2978161329C120665830 @default.
- W2978161329 hasConceptScore W2978161329C121332964 @default.
- W2978161329 hasConceptScore W2978161329C124101348 @default.
- W2978161329 hasConceptScore W2978161329C124952713 @default.
- W2978161329 hasConceptScore W2978161329C138885662 @default.
- W2978161329 hasConceptScore W2978161329C142362112 @default.
- W2978161329 hasConceptScore W2978161329C154945302 @default.
- W2978161329 hasConceptScore W2978161329C177264268 @default.
- W2978161329 hasConceptScore W2978161329C192209626 @default.
- W2978161329 hasConceptScore W2978161329C199360897 @default.
- W2978161329 hasConceptScore W2978161329C2776145971 @default.
- W2978161329 hasConceptScore W2978161329C2776401178 @default.
- W2978161329 hasConceptScore W2978161329C2780801425 @default.
- W2978161329 hasConceptScore W2978161329C2780980858 @default.
- W2978161329 hasConceptScore W2978161329C41008148 @default.
- W2978161329 hasConceptScore W2978161329C41895202 @default.
- W2978161329 hasConceptScore W2978161329C5274069 @default.
- W2978161329 hasConceptScore W2978161329C55166926 @default.
- W2978161329 hasConceptScore W2978161329C73555534 @default.
- W2978161329 hasConceptScore W2978161329C94124525 @default.
- W2978161329 hasConceptScore W2978161329C96146094 @default.
- W2978161329 hasLocation W29781613291 @default.
- W2978161329 hasOpenAccess W2978161329 @default.
- W2978161329 hasPrimaryLocation W29781613291 @default.
- W2978161329 hasRelatedWork W120286951 @default.
- W2978161329 hasRelatedWork W1838330068 @default.
- W2978161329 hasRelatedWork W2044224802 @default.
- W2978161329 hasRelatedWork W2103137496 @default.
- W2978161329 hasRelatedWork W2111478152 @default.
- W2978161329 hasRelatedWork W2296059120 @default.
- W2978161329 hasRelatedWork W254202083 @default.
- W2978161329 hasRelatedWork W2572900683 @default.
- W2978161329 hasRelatedWork W2586598639 @default.
- W2978161329 hasRelatedWork W2731646070 @default.
- W2978161329 hasRelatedWork W2741312414 @default.
- W2978161329 hasRelatedWork W2765885542 @default.
- W2978161329 hasRelatedWork W2902479064 @default.
- W2978161329 hasRelatedWork W2902557560 @default.
- W2978161329 hasRelatedWork W2918055175 @default.
- W2978161329 hasRelatedWork W3097574897 @default.
- W2978161329 hasRelatedWork W3108414243 @default.
- W2978161329 hasRelatedWork W3185133004 @default.
- W2978161329 hasRelatedWork W3192354942 @default.
- W2978161329 hasRelatedWork W59786464 @default.
- W2978161329 isParatext "false" @default.
- W2978161329 isRetracted "false" @default.