Journal
NEUROCOMPUTING
Volume 470, Issue -, Pages 344-351Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2021.05.105
Keywords
Interpretable machine learning; Metric learning; Nearest neighbors
Categories
Funding
- Honda Research Institute Europe
Ask authors/readers for more resources
To improve the performance of automated systems, we have developed a method that allows learning locally adaptive metrics in the k nearest neighbors algorithm, making it more effective and interpretable in real-world applications.
When training automated systems, it has been shown to be beneficial to adapt the representation of data by learning a problem-specific metric. This metric is global. We extend this idea and, for the widely used family of k nearest neighbors algorithms, develop a method that allows learning locally adaptive metrics. These local metrics not only improve performance, but are naturally interpretable. To demonstrate important aspects of how our approach works, we conduct a number of experiments on synthetic data sets, and we show its usefulness on real-world benchmark data sets. (c) 2021 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available