Article (Scientific journals)
The Effect of Noise Level on the Accuracy of Causal Discovery Methods with Additive Noise Models
Kap, Benjamin; Aleksandrova, Marharyta; Engel, Thomas
2022In Communications in Computer and Information Science, 1530
Peer reviewed
 

Files


Full Text
2021_BNAIC_noise_impact_causality.pdf
Author preprint (577.46 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Causal Learning; Additive Noise Models; Noise Level
Abstract :
[en] In recent years a lot of research was conducted within the area of causal inference and causal learning. Many methods were developed to identify the cause-effect pairs. These methods also proved their ability to successfully determine the direction of causal relationships from observational real-world data. Yet in bivariate situations, causal discovery problems remain challenging. A class of methods, that also allows tackling the bivariate case, is based on Additive Noise Models (ANMs). Unfortunately, one aspect of these methods has not received much attention until now: what is the impact of different noise levels on the ability of these methods to identify the direction of the causal relationship? This work aims to bridge this gap with the help of an empirical study. We consider a bivariate case and two specific methods Regression with Subsequent Independence Test and Identification using Conditional Variances. We perform a set of experiments with an exhaustive range of ANMs where the additive noises’ levels gradually change from 1% to 10000% of the causes’ noise level (the latter remains fixed). Additionally, we consider several different types of distributions as well as linear and non-linear ANMs. The results of the experiments show that these causal discovery methods can fail to capture the true causal direction for some levels of noise.
Disciplines :
Computer science
Author, co-author :
Kap, Benjamin ;  University of Luxembourg
Aleksandrova, Marharyta ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Engel, Thomas ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
External co-authors :
no
Language :
English
Title :
The Effect of Noise Level on the Accuracy of Causal Discovery Methods with Additive Noise Models
Publication date :
2022
Journal title :
Communications in Computer and Information Science
ISSN :
1865-0929
Publisher :
Springer, Berlin, Germany
Special issue title :
Artificial Intelligence and Machine Learning. BNAIC/Benelearn 2021
Volume :
1530
Peer reviewed :
Peer reviewed
Available on ORBilu :
since 26 February 2022

Statistics


Number of views
156 (4 by Unilu)
Number of downloads
167 (5 by Unilu)

Scopus citations®
 
2
Scopus citations®
without self-citations
2
OpenCitations
 
0

Bibliography


Similar publications



Contact ORBilu