Local Distance Metric Learning for Nearest Neighbor Algorithm
This work addresses the challenge of improving nearest neighbor classifiers for machine learning applications with non-uniform data distributions, representing an incremental advance in local metric learning.
The paper tackled the problem of irregular data distributions in nearest neighbor classification by proposing Local Mahalanobis Distance Learning (LMDL), a method that learns multiple local distance metrics using prototypes, and showed it outperforms state-of-the-art methods in experiments on various datasets.
Distance metric learning is a successful way to enhance the performance of the nearest neighbor classifier. In most cases, however, the distribution of data does not obey a regular form and may change in different parts of the feature space. Regarding that, this paper proposes a novel local distance metric learning method, namely Local Mahalanobis Distance Learning (LMDL), in order to enhance the performance of the nearest neighbor classifier. LMDL considers the neighborhood influence and learns multiple distance metrics for a reduced set of input samples. The reduced set is called as prototypes which try to preserve local discriminative information as much as possible. The proposed LMDL can be kernelized very easily, which is significantly desirable in the case of highly nonlinear data. The quality as well as the efficiency of the proposed method assesses through a set of different experiments on various datasets and the obtained results show that LDML as well as the kernelized version is superior to the other related state-of-the-art methods.