Dimensionality Invariant Similarity Measure
This addresses the problem of dimensionality sensitivity in similarity measures for machine learning practitioners, but it appears incremental as it builds on existing metric-based approaches.
The paper introduces a new similarity measure that is invariant to large differences in some dimensions, and experiments show it is promising for KNN classification on real datasets.
This paper presents a new similarity measure to be used for general tasks including supervised learning, which is represented by the K-nearest neighbor classifier (KNN). The proposed similarity measure is invariant to large differences in some dimensions in the feature space. The proposed metric is proved mathematically to be a metric. To test its viability for different applications, the KNN used the proposed metric for classifying test examples chosen from a number of real datasets. Compared to some other well known metrics, the experimental results show that the proposed metric is a promising distance measure for the KNN classifier with strong potential for a wide range of applications.