Weak supervision and other non-standard classification problems: A taxonomy

Hernández-González, Jerónimo; Inza, Iñaki; Lozano, José A.

doi:10.1016/j.patrec.2015.10.008

Cited by 78 publications

(38 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of this increased necessity, new related research avenues are explored every year. In this sense, the recently coined term weak supervision [1] refers to those classification machine learning problems where the labelling information is not as accessible as in the fully-supervised problem (where a label is associated to each pattern). The problem of semi-supervised learning (i.e.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised learning for ordinal Kernel Discriminant Analysis

et al. 2016

View full text Add to dashboard Cite

Ordinal classification considers those classification problems where the labels of the variable to predict follow a given order. Naturally, labelled data is scarce or difficult to obtain in this type of problems because, in many cases, ordinal labels are given by an user or expert (e.g. in recommendation systems). Firstly, this paper develops a new strategy for ordinal classification where both labelled and unlabelled data are used in the model construction step (a scheme which is referred to as semi-supervised learning). More specifically, the ordinal version of kernel discriminant learning is extended for this setting considering the neighbourhood information of unlabelled data, which is proposed to be computed in the feature space induced by the kernel function. Secondly, a new method for semi-supervised kernel learning is devised in the context of ordinal classification, which is combined with our developed classification strategy to optimise the kernel parameters. The experiments conducted compare 6 different approaches for semi-supervised learning in the context of ordinal classification in a battery of 30 datasets, showing 1) the good synergy of the ordinal version of discriminant analysis and the use of unlabelled data and 2) the advantage of computing distances in the feature space induced by the kernel function.

show abstract

Section: Introductionmentioning

confidence: 99%

Semi-supervised learning for ordinal Kernel Discriminant Analysis

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Crowdsourcing is a way of addressing a problem collaboratively and has become an important technique for dealing with software requirements, design, development, testing and decision making. In machine learning, learning from crowds [8,9] is a weakly supervised classification problem [39] where the examples provided for model training are unreliably categorized by a set of annotators of questionable trustfulness and the ground truth is unavailable. Although such labeling usually shows disagreements among annotators (see Figure 1 for a graphical representation), competitive classifiers can be learnt from their combination.…”

Section: Learning From Crowdsmentioning

confidence: 99%

Learning to classify software defects from crowds: A novel approach

Hernández-González

Rodríguez

Inza

et al. 2018

Applied Soft Computing

Self Cite

View full text Add to dashboard Cite

In software engineering, associating each reported defect with a category allows, among many other things, for the appropriate allocation of resources. Although this classification task can be automated using standard machine learning techniques, the categorization of defects for model training requires expert knowledge, which is not always available. To circumvent this dependency, we propose to apply the learning from crowds paradigm, where training categories are obtained from multiple non-expert annotators (and so may be incomplete, noisy or erroneous) and, dealing with this subjective class information, classifiers are efficiently learnt. To illustrate our proposal, we present two real applications of the IBM's orthogonal defect classification working on the issue tracking systems from two different real domains. Bayesian network classifiers learnt using two state-of-the-art methodologies from data labeled by a crowd of annotators are used to predict the category (impact) of reported software defects. The considered methodologies show enhanced performance regarding the straightforward solution (majority voting) according to different metrics. This shows the possibilities of using non-expert knowledge aggregation techniques when expert knowledge is unavailable.

show abstract

“…They are necessary to train the classification models as well as to evaluate them. The classification task at hand is a weakly supervised classification problem (Hernández-González et al, 2016); specifically, a positive-unlabeled classification problem (Calvo et al, 2007) where only positive examples are available for training: the pairs of entities related by a equivalentTo relationship. No negative example, understood as a pair of nodes in different language subgraphs which are not suitable to hold an equivalentTo relationship, is available.…”

Section: Training Examplesmentioning

confidence: 99%

Merging knowledge bases in different languages

Hernández-González

Hruschka

Mitchell

2017

Proceedings of TextGraphs-11: The Workshop on Graph-Based Methods For Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Recently, different systems which learn to populate and extend a knowledge base (KB) from the web in different languages have been presented. Although a large set of concepts should be learnt independently from the language used to read, there are facts which are expected to be more easily gathered in local language (e.g., culture or geography). A system that merges KBs learnt in different languages will benefit from the complementary information as long as common beliefs are identified, as well as from redundancy present in web pages written in different languages. In this paper, we deal with the problem of identifying equivalent beliefs (or concepts) across language specific KBs, assuming that they share the same ontology of categories and relations. In a case study with two KBs independently learnt from different inputs, namely web pages written in English and web pages written in Portuguese respectively, we report on the results of two methodologies: an approach based on personalized PageRank and an inference technique to find out common relevant paths through the KBs. The proposed inference technique efficiently identifies relevant paths, outperforming the baseline (a dictionary-based classifier) in the vast majority of tested categories.

show abstract

Weak supervision and other non-standard classification problems: A taxonomy

Cited by 78 publications

References 14 publications

Semi-supervised learning for ordinal Kernel Discriminant Analysis

Semi-supervised learning for ordinal Kernel Discriminant Analysis

Learning to classify software defects from crowds: A novel approach

Merging knowledge bases in different languages

Contact Info

Product

Resources

About