A Locally Adaptive Multi-Label k-Nearest Neighbor Algorithm

Wang, D, Wang, J, Hu, F, Li, L and Zhang, X 2018, 'A Locally Adaptive Multi-Label k-Nearest Neighbor Algorithm', in PAKDD 2018: Advances in Knowledge Discovery and Data Mining, Melbourne, Australia, 3-6 June 2018, pp. 81-93.


Document type: Conference Paper
Collection: Conference Papers

Title A Locally Adaptive Multi-Label k-Nearest Neighbor Algorithm
Author(s) Wang, D
Wang, J
Hu, F
Li, L
Zhang, X
Year 2018
Conference name The 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2018)
Conference location Melbourne, Australia
Conference dates 3-6 June 2018
Proceedings title PAKDD 2018: Advances in Knowledge Discovery and Data Mining
Publisher Springer
Place of publication Switzerland
Start page 81
End page 93
Total pages 13
Abstract In the field of multi-label learning, ML-kNN is the first lazy learning approach and one of the most influential approaches. The main idea of it is to adapt k-NN method to deal with multi-label data, where maximum a posteriori rule is utilized to adaptively adjust decision boundary for each unseen instance. In ML-kNN, all test instances which get the same number of votes among k nearest neighbors have the same probability to be assigned a label, which may cause improper decision since it ignores the local difference of samples. Actually, in real world data sets, the instances with (or without) label l from different locations may have different numbers of neighbors with the label l. In this paper, we propose a locally adaptive Multi-Label k-Nearest Neighbor method to address this problem, which takes the local difference of samples into account. We show how a simple modification to the posterior probability expression, previously used in ML-kNN algorithm, allows us to take the local difference into account. Experimental results on benchmark data sets demonstrate that our approach has superior classification performance with respect to other kNN-based algorithms.
Subjects Pattern Recognition and Data Mining
DOI - identifier 10.1007/978-3-319-93034-3_7
ISBN 9783319930336
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Altmetric details:
Access Statistics: 40 Abstract Views  -  Detailed Statistics
Created: Thu, 21 Feb 2019, 12:10:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us