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.
%0 Journal Article
%1 zhou2017brief
%A Zhou, Zhi-Hua
%D 2017
%J National Science Review
%K introduction learning machine ml supervised weakly
%N 1
%P 44-53
%R 10.1093/nsr/nwx106
%T A brief introduction to weakly supervised learning
%U https://doi.org/10.1093/nsr/nwx106
%V 5
%X 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.
@article{zhou2017brief,
abstract = {{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.}},
added-at = {2021-03-12T16:11:25.000+0100},
author = {Zhou, Zhi-Hua},
biburl = {https://www.bibsonomy.org/bibtex/261fe5360dd74d89b019c3ddda4f21b47/jaeschke},
doi = {10.1093/nsr/nwx106},
eprint = {https://academic.oup.com/nsr/article-pdf/5/1/44/31567770/nwx106.pdf},
interhash = {cecf8331d9b456fb65044226c651c297},
intrahash = {61fe5360dd74d89b019c3ddda4f21b47},
issn = {2095-5138},
journal = {National Science Review},
keywords = {introduction learning machine ml supervised weakly},
month = {08},
number = 1,
pages = {44-53},
timestamp = {2021-03-12T16:11:25.000+0100},
title = {A brief introduction to weakly supervised learning},
url = {https://doi.org/10.1093/nsr/nwx106},
volume = 5,
year = 2017
}