Join Path-Based Data Augmentation for Decision Trees

Conference Paper (2022)
Author(s)

A. Ionescu (TU Delft - Web Information Systems)

R. Hai (TU Delft - Web Information Systems)

M. Fragkoulis (Delivery Hero SE)

A Katsifodimos (TU Delft - Web Information Systems)

Research Group
Web Information Systems
Copyright
© 2022 A. Ionescu, R. Hai, M. Fragkoulis, A Katsifodimos
DOI related publication
https://doi.org/10.1109/ICDEW55742.2022.00018
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 A. Ionescu, R. Hai, M. Fragkoulis, A Katsifodimos
Research Group
Web Information Systems
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.@en
Pages (from-to)
84-88
ISBN (print)
978-1-6654-8105-2
ISBN (electronic)
978-1-6654-8104-5
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Machine Learning (ML) applications require high-quality datasets. Automated data augmentation techniques can help increase the richness of training data, thus increasing the ML model accuracy. Existing solutions focus on efficiency and ML model accuracy but do not exploit the richness of dataset relationships. With relational data, the challenge lies in identifying join paths that best augment a feature table to increase the performance of a model. In this paper we propose a two-step, automated data augmentation approach for relational data that involves: (i) enumerating join paths of various lengths given a base table and (ii) ranking the join paths using filter methods for feature selection. We show that our approach can improve prediction accuracy and reduce runtime compared to the baseline approach.

Files

Join_Path_Based_Data_Augmentat... (pdf)
(pdf | 0.446 Mb)
- Embargo expired in 01-07-2023
License info not available