FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2069735839> ?p ?o ?g. }

• W2069735839 endingPage "46" @default.
• W2069735839 startingPage "1" @default.
• W2069735839 abstract "Supervised learning—that is, learning from labeled examples—is an area of Machine Learning that has reached substantial maturity. It has generated general-purpose and practically successful algorithms and the foundations are quite well understood and captured by theoretical frameworks such as the PAC-learning model and the Statistical Learning theory framework. However, for many contemporary practical problems such as classifying web pages or detecting spam, there is often additional information available in the form of unlabeled data, which is often much cheaper and more plentiful than labeled data. As a consequence, there has recently been substantial interest in semi-supervised learning—using unlabeled data together with labeled data—since any useful information that reduces the amount of labeled data needed can be a significant benefit. Several techniques have been developed for doing this, along with experimental results on a variety of different learning problems. Unfortunately, the standard learning frameworks for reasoning about supervised learning do not capture the key aspects and the assumptions underlying these semi -supervised learning methods. In this article, we describe an augmented version of the PAC model designed for semi-supervised learning, that can be used to reason about many of the different approaches taken over the past decade in the Machine Learning community. This model provides a unified framework for analyzing when and why unlabeled data can help, in which one can analyze both sample-complexity and algorithmic issues. The model can be viewed as an extension of the standard PAC model where, in addition to a concept class C , one also proposes a compatibility notion: a type of compatibility that one believes the target concept should have with the underlying distribution of data. Unlabeled data is then potentially helpful in this setting because it allows one to estimate compatibility over the space of hypotheses, and to reduce the size of the search space from the whole set of hypotheses C down to those that, according to one's assumptions, are a-priori reasonable with respect to the distribution. As we show, many of the assumptions underlying existing semi-supervised learning algorithms can be formulated in this framework. After proposing the model, we then analyze sample-complexity issues in this setting: that is, how much of each type of data one should expect to need in order to learn well, and what the key quantities are that these numbers depend on. We also consider the algorithmic question of how to efficiently optimize for natural classes and compatibility notions, and provide several algorithmic results including an improved bound for Co-Training with linear separators when the distribution satisfies independence given the label." @default.
• W2069735839 created "2016-06-24" @default.
• W2069735839 creator A5024803432 @default.
• W2069735839 creator A5068544954 @default.
• W2069735839 date "2010-03-01" @default.
• W2069735839 modified "2023-10-14" @default.
• W2069735839 title "A discriminative model for semi-supervised learning" @default.
• W2069735839 cites W112090490 @default.
• W2069735839 cites W1507695921 @default.
• W2069735839 cites W1520252399 @default.
• W2069735839 cites W1560659665 @default.
• W2069735839 cites W1564947197 @default.
• W2069735839 cites W1572372689 @default.
• W2069735839 cites W1974411071 @default.
• W2069735839 cites W1995897489 @default.
• W2069735839 cites W2014902932 @default.
• W2069735839 cites W2015194364 @default.
• W2069735839 cites W2024574617 @default.
• W2069735839 cites W2037603696 @default.
• W2069735839 cites W2040443294 @default.
• W2069735839 cites W2045313701 @default.
• W2069735839 cites W2047430378 @default.
• W2069735839 cites W2048679005 @default.
• W2069735839 cites W2056707879 @default.
• W2069735839 cites W2061526129 @default.
• W2069735839 cites W2081177492 @default.
• W2069735839 cites W2083515729 @default.
• W2069735839 cites W2087258353 @default.
• W2069735839 cites W2097089247 @default.
• W2069735839 cites W2101210369 @default.
• W2069735839 cites W2106078714 @default.
• W2069735839 cites W2106491486 @default.
• W2069735839 cites W2114232233 @default.
• W2069735839 cites W2131775048 @default.
• W2069735839 cites W2143362693 @default.
• W2069735839 cites W2151023586 @default.
• W2069735839 cites W2154794763 @default.
• W2069735839 cites W2154952480 @default.
• W2069735839 cites W2426031434 @default.
• W2069735839 cites W4230674625 @default.
• W2069735839 cites W4238893454 @default.
• W2069735839 doi "https://doi.org/10.1145/1706591.1706599" @default.
• W2069735839 hasPublicationYear "2010" @default.
• W2069735839 type Work @default.
• W2069735839 sameAs 2069735839 @default.
• W2069735839 citedByCount "109" @default.
• W2069735839 countsByYear W20697358392012 @default.
• W2069735839 countsByYear W20697358392013 @default.
• W2069735839 countsByYear W20697358392014 @default.
• W2069735839 countsByYear W20697358392015 @default.
• W2069735839 countsByYear W20697358392016 @default.
• W2069735839 countsByYear W20697358392017 @default.
• W2069735839 countsByYear W20697358392018 @default.
• W2069735839 countsByYear W20697358392019 @default.
• W2069735839 countsByYear W20697358392020 @default.
• W2069735839 countsByYear W20697358392021 @default.
• W2069735839 countsByYear W20697358392022 @default.
• W2069735839 countsByYear W20697358392023 @default.
• W2069735839 crossrefType "journal-article" @default.
• W2069735839 hasAuthorship W2069735839A5024803432 @default.
• W2069735839 hasAuthorship W2069735839A5068544954 @default.
• W2069735839 hasBestOaLocation W20697358391 @default.
• W2069735839 hasConcept C115903097 @default.
• W2069735839 hasConcept C119857082 @default.
• W2069735839 hasConcept C136197465 @default.
• W2069735839 hasConcept C136389625 @default.
• W2069735839 hasConcept C154945302 @default.
• W2069735839 hasConcept C24138899 @default.
• W2069735839 hasConcept C2777212361 @default.
• W2069735839 hasConcept C32254414 @default.
• W2069735839 hasConcept C41008148 @default.
• W2069735839 hasConcept C50292564 @default.
• W2069735839 hasConcept C50644808 @default.
• W2069735839 hasConcept C58973888 @default.
• W2069735839 hasConcept C8038995 @default.
• W2069735839 hasConcept C97931131 @default.
• W2069735839 hasConceptScore W2069735839C115903097 @default.
• W2069735839 hasConceptScore W2069735839C119857082 @default.
• W2069735839 hasConceptScore W2069735839C136197465 @default.
• W2069735839 hasConceptScore W2069735839C136389625 @default.
• W2069735839 hasConceptScore W2069735839C154945302 @default.
• W2069735839 hasConceptScore W2069735839C24138899 @default.
• W2069735839 hasConceptScore W2069735839C2777212361 @default.
• W2069735839 hasConceptScore W2069735839C32254414 @default.
• W2069735839 hasConceptScore W2069735839C41008148 @default.
• W2069735839 hasConceptScore W2069735839C50292564 @default.
• W2069735839 hasConceptScore W2069735839C50644808 @default.
• W2069735839 hasConceptScore W2069735839C58973888 @default.
• W2069735839 hasConceptScore W2069735839C8038995 @default.
• W2069735839 hasConceptScore W2069735839C97931131 @default.
• W2069735839 hasFunder F4320306076 @default.
• W2069735839 hasFunder F4320337389 @default.
• W2069735839 hasIssue "3" @default.
• W2069735839 hasLocation W20697358391 @default.
• W2069735839 hasLocation W20697358392 @default.
• W2069735839 hasOpenAccess W2069735839 @default.
• W2069735839 hasPrimaryLocation W20697358391 @default.
• W2069735839 hasRelatedWork W161531308 @default.

• next