1 Class Conditional Nearest Neighbor and Large Margin Instance Selection

1 Class Conditional Nearest Neighbor and Large Margin Instance Selection

Cached

Download Links

[www.cs.ru.nl]

by Elena Marchiori

BibTeX

@MISC{Marchiori_1class,
    author = {Elena Marchiori},
    title = {1 Class Conditional Nearest Neighbor and Large Margin Instance Selection},
    year = {}
}

Bookmark

OpenURL

Abstract

Abstract—The one nearest neighbor (1-NN) rule uses instance proximity followed by class labeling information for classifying new instances. This paper presents a framework for studying properties of the training set related to proximity and labeling information, in order to improve the performance of the 1-NN rule. To this aim, a so-called class conditional nearest neighbor (c.c.n.n.) relation is introduced, consisting of those pairs of training instances (a, b) such that b is the nearest neighbor of a among those instances (excluded a) in one of the classes of the training set. A graph-based representation of c.c.n.n. is used for a comparative analysis of c.c.n.n. and of other interesting proximity-based concepts. In particular, a scoring function on instances is introduced, which measures the effect of removing one instance on the hypothesis-margin of other instances. This scoring function is employed to develop an effective large margin instance selection algorithm, which is empirically demonstrated to improve storage and accuracy performance of the 1-NN rule on artificial and real-life data sets.

Citations

6695	Statistical Learning Theory - Vapnik - 1998
1714	Schapire R: A decision-theoretic generalization of online learning and an application to boosting - Freund - 1997
1493	Vapnik V: Support-Vector Networks - Cortes - 1995
897	Instance-Based Learning Algorithms - Aha, Kibler, et al. - 1991
688	Nearest neighbor pattern classification - Cover, Hart - 1967
606	W: Boosting the Margin: A New Explanation for the Effectiveness of Voting Methods. The Annals of Statistics - Schapire, Freund, et al. - 1998
298	Divergence measures based on the Shannon entropy - Lin - 1991
199	Soft margins for AdaBoost - Ratsch, Onoda, et al. - 1998
177	Distance metric learning for large margin nearest neighbor classification - Weinberger, Saul
150	Two algorithms for nearest-neighbor search in high dimensions - Kleinberg - 1997
120	Statistical Comparisons of Classifiers over Multiple Data Sets - Demšar - 2006
93	Reduction techniques for instance-based learning algorithms - WILSON, MARTINEZ
90	Semi-supervised classification by low density separation - Chapelle, Zien - 2005
70	The ordering of multivariate data - Barnett - 1976
55	D.: Locally adaptive metric nearest-neighbor classification - Domeniconi, Peng, et al. - 2002
55	Instance Pruning Techniques - Wilson, Martinez - 1997
42	Advances in instance selection for instance-based learning algorithms - Brighton, Mellish
28	For valid generalization, the size of the weights is more important than the size of the network - Bartlett - 1997
28	Margin based feature selection – theory and algorithms - Gilad-Bachrach, Navot, et al.
20	Minimal consistent set (mcs) identification for optimal nearest neighbor decision systems design - Dasarathy - 1994
19	Margin analysis of the LVQ algorithm - Crammer, Gilad-Bachrach, et al. - 2002
19	Prototype selection for dissimilarity-based classifiers - Pekalska, Duin, et al. - 2006
15	On the generalization ability of GRLVQ networks - Hammer, Strickert, et al. - 2005
15	C.: On the consistency of information filters for lazy learning algorithms - Brighton, Mellish - 1999
14	M (2004) Comparison of Instances Selection Algorithms I. Algorithms Survey - Jankowski, Grochowski
14	Proximity graphs for nearest neighbor decision rules: recent progress - Toussaint - 2002
11	Fast implementation of nearest neighbor classifiers - Grother, Candela, et al. - 1997
11	Nearest neighbor classifier: simultaneous editing and feature selection - Kuncheva, Jain - 1999
11	Learning weighted metrics to minimize nearest-neighbor classification error - Paredes, Vidal - 2006
11	Adaptive Quasiconformal Kernel Nearest Neighbor Classification - Peng, Heisterkamp, et al.
8	2007: Improving the Nearest Neighbor rule with a simple adaptive distance measure - Wang, Neskovic, et al.
7	Nearest unlike neighbor (NUN): an aid to decision confidence estimation - Dasarathy - 1995
4	Neighborhood property based pattern selection for support vector machines, Neural Comput 19 - Shin, Cho - 2007
4	Simultaneous feature selection and feature weighting using hybrid tabu search/k-nearest neighbor classifier - Tahir, Bouridane, et al.
3	An analysis of how training data complexity affects the nearest neighbor classifiers - Sánchez, Mollineda, et al.
2	Fast nearest neighbor condensation for large data sets classification - Angiulli
2	Distributed nearest neighbor-based condensation of very large data sets - Angiulli, Folino
2	A memetic algorithm for evolutionary prototype selection: A scaling up approach - García, Cano, et al.
1	Fuzzy understanding of neighborhoods with nearest unlike neighbor sets - Dasarathy - 1995
1	Voronoi networks and their probability of misclassification - Krishna, Thathachar, et al. - 2000
1	Hit miss networks with applications to instance selection - Marchiori
1	Map pattern reconstruction from sample data; Mississippi Delta region of southeast Louisiana - McCammon - 1972