Using Weighted Nearest Neighbor to Benefit from Unlabeled Data

Driessens, Kurt; Reutemann, Peter; Pfahringer, Bernhard; Leschi, Claire

doi:10.1007/11731139_10

Cited by 41 publications

(37 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Driessens et al [16] presented a two-stage classifier, YATSI, that improves its predictive accuracy by making use of the available unlabeled data. It used a weighted nearest neighbor classification algorithm using the combined examplesets as a knowledge base.…”

Section: Example 1 In the All-aml Leukaemia Gene Expression Datasetmentioning

confidence: 99%

Improving k-Nearest Neighbour Classification with Distance Functions Based on Receiver Operating Characteristics

Hassan

Hossain

Bailey

et al.

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

Abstract. The k-nearest neighbour (k-NN) technique, due to its interpretable nature, is a simple and very intuitively appealing method to address classification problems. However, choosing an appropriate distance function for k-NN can be challenging and an inferior choice can make the classifier highly vulnerable to noise in the data. In this paper, we propose a new method for determining a good distance function for k-NN. Our method is based on consideration of the area under the Receiver Operating Characteristics (ROC) curve, which is a well known method to measure the quality of binary classifiers. It computes weights for the distance function, based on ROC properties within an appropriate neighbourhood for the instances whose distance is being computed. We experimentally compare the effect of our scheme with a number of other well-known k-NN distance metrics, as well as with a range of different classifiers. Experiments show that our method can substantially boost the classification performance of the k-NN algorithm. Furthermore, in a number of cases our technique is even able to deliver better accuracy than state-of-the-art non k-NN classifiers, such as support vector machines.

show abstract

Section: Example 1 In the All-aml Leukaemia Gene Expression Datasetmentioning

confidence: 99%

Improving k-Nearest Neighbour Classification with Distance Functions Based on Receiver Operating Characteristics

Hassan

Hossain

Bailey

et al.

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

show abstract

“…Catal and Diri (2009) proposed the immune-based YATSI (Yet Another Two Stage Idea) (Driessens, 2006) algorithm to predict faulty software, which is a semisupervised meta-algorithm that can be wrapped around any supervised (base) classifier.…”

Section: Related Workmentioning

confidence: 99%

An empirical study of self-training and data balancing techniques for splice site prediction

Stănescu

Caragea

2017

IJBRA

View full text Add to dashboard Cite

Thanks to Next Generation Sequencing technologies, unlabelled data is now generated easily, while the annotation process remains expensive. Semi-supervised learning represents a cost-effective alternative to supervised learning, as it can improve supervised classifiers by making use of unlabelled data. However, semi-supervised learning has not been studied much for problems with highly skewed class distributions, which are prevalent in bioinformatics. To address this limitation, we carry out a study of a semi-supervised learning algorithm, specifically self-training based on Naïve Bayes, with focus on data-level approaches for handling imbalanced class distributions. Our study is conducted on the problem of predicting splice sites and it is based on datasets for which the ratio of positive to negative examples is 1-to-99. Our results show that under certain conditions semi-supervised learning algorithms are a better choice than purely supervised classification algorithms.

show abstract

“…And graphs are introduced in semi-supervised learning [14]. Work in [10][13] [15] is most related to our work. [10] proposed a semi-supervised learning based on a Gaussian random field model.…”

Section: Related Workmentioning

confidence: 99%

“…Different from [10] and [13], we present an efficient iterative algorithm for large data sets and for circumstances where matrix computation fails because of the nonexistent inverse matrix. [15] introduced a two-stage approach. In the first stage, a model is built based on training data.…”

Section: Related Workmentioning

confidence: 99%

Kernel-Based Transductive Learning with Nearest Neighbors

Shu

Lei

et al. 2009

Advances in Data and Web Management

View full text Add to dashboard Cite

Abstract. In the k-nearest neighbor (KNN) classifier, nearest neighbors involve only labeled data. That makes it inappropriate for the data set that includes very few labeled data. In this paper, we aim to solve the classification problem by applying transduction to the KNN algorithm. We consider two groups of nearest neighbors for each data point -one from labeled data, and the other from unlabeled data. A kernel function is used to assign weights to neighbors. We derive the recurrence relation of neighboring data points, and then present two solutions to the classification problem. One solution is to solve it by matrix computation for small or medium-size data sets. The other is an iterative algorithm for large data sets, and in the iterative process an energy function is minimized. Experiments show that our solutions achieve high performance and our iterative algorithm converges quickly.

show abstract

Using Weighted Nearest Neighbor to Benefit from Unlabeled Data

Cited by 41 publications

References 7 publications

Improving k-Nearest Neighbour Classification with Distance Functions Based on Receiver Operating Characteristics

Improving k-Nearest Neighbour Classification with Distance Functions Based on Receiver Operating Characteristics

An empirical study of self-training and data balancing techniques for splice site prediction

Kernel-Based Transductive Learning with Nearest Neighbors

Contact Info

Product

Resources

About