Who Cited It

A brief introduction to weakly supervised learning

2017 · National Science Review · 1,911 citations · 1 from inside this corpus

Zhi‐Hua Zhou

Supervised learning techniques construct predictive models by learning from a large number of training examples, where each training example has a label indicating its ground-truth output. Though current techniques have achieved great success, it is noteworthy that in many tasks it is difficult to get strong supervision information like fully ground-truth labels due to the high cost of the data-labeling process. Thus, it is desirable for machine-learning techniques to work with weak supervision. This article reviews some research progress of weakly supervised learning, focusing on three typical types of weak supervision: incomplete supervision, where only a subset of training data is given with labels; inexact supervision, where the training data are given with only coarse-grained labels; and inaccurate supervision, where the given labels are not always ground-truth.

A brief introduction to weakly supervised learning (2017)A brief introduction to weakl…Reinforcement Learning: An Introduction (1998)Reinforcement Learning: An In…Reinforcement Learning: An Introduction (2005)Reinforcement Learning: An In…Deep Learning (2016)Deep LearningSemi-Supervised Learning (2006)Semi-Supervised LearningSemi-Supervised Learning Literature Survey (2005)Semi-Supervised Learning Lite…A Review on Multi-Label Learning Algorithms (2013)A Review on Multi-Label Learn…Text Classification from Labeled and Unlabeled Documents using EM (2000)Text Classification from Labe…Ensemble Methods (2012)Ensemble MethodsEnsemble Methods: Foundations and Algorithms (2012)Ensemble Methods: Foundations…Classification in the Presence of Label Noise: A Survey (2014)Classification in the Presenc…Generalizing from a Few Examples (2020)Generalizing from a Few Examp…
11 of 11 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.
this paper works it cites works citing it node size = global citations · hover for the full title

What this paper cites, inside the corpus

PaperYearCited
Reinforcement Learning: An Introduction199827,409
Reinforcement Learning: An Introduction200525,758
Deep Learning20168,952
Semi-Supervised Learning20064,334
Semi-Supervised Learning Literature Survey20053,879
A Review on Multi-Label Learning Algorithms20133,375
Text Classification from Labeled and Unlabeled Documents using EM20002,753
Ensemble Methods20122,469
Ensemble Methods: Foundations and Algorithms20122,064
Classification in the Presence of Label Noise: A Survey20141,777

What cites it, inside the corpus

PaperYearCited
Generalizing from a Few Examples20202,761

Links

DOI · Open access copy · OpenAlex record

Topics

Machine Learning and Data ClassificationComputer Science
Machine Learning and AlgorithmsComputer Science
Anomaly Detection Techniques and ApplicationsComputer Science

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

  • supports1 author record(s) attached.
  • supports114 reference(s) recorded.
  • neutralThe DOI carries no year to check against.
  • supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:52+00:00.

sha256 930f5bc64fea8a60…