Please use this identifier to cite or link to this item:
Title: Copying Machine Learning Classifiers
Author: Unceta, Irene
Nin, Jordi
Pujol Vila, Oriol
Keywords: Aprenentatge automàtic
Models matemàtics
Machine learning
Mathematical models
Issue Date: 14-Sep-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Abstract: We study copying of machine learning classifiers, an agnostic technique to replicate the decision behavior of any classifier. We develop the theory behind the problem of copying, highlighting its properties, and propose a framework to copy the decision behavior of any classifier using no prior knowledge of its parameters or training data distribution. We validate this framework through extensive experiments using data from a series of well-known problems. To further validate this concept, we use three different use cases where desiderata such as interpretability, fairness or productivization constrains need to be addressed. Results show that copies can be exploited to enhance existing solutions and improve them adding new features and characteristics.
Note: Reproducció del document publicat a:
It is part of: IEEE Access, 2020, vol. 8, p. 160268-160284
Related resource:
ISSN: 2169-3536
Appears in Collections:Articles publicats en revistes (Matemàtiques i Informàtica)

Files in This Item:
File Description SizeFormat 
702957.pdf3.51 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons