No full text
Unpublished conference/Abstract (Scientific congresses, symposiums and conference proceedings)
The need of standardised metadata to encode causal relationships: Towards safer data-driven machine learning biological solutions
Garcia Santa Cruz, Beatriz; Vega Moreno, Carlos Gonzalo; Hertel, Frank
2021Computational Intelligence Methods for Bioinformatics and Biostatistics 2021
 

Files


Full Text
No document available.

Send to



Details



Keywords :
confounders; causality; metadata; machine learning; systems biology
Abstract :
[en] In this paper, we discuss the importance of considering causal relations in the development of machine learning solutions to prevent factors hampering the robustness and generalisation capacity of the models, such as induced biases. This issue often arises when the algorithm decision is affected by confounding factors. In this work, we argue that the integration of causal relationships can identify potential confounders. We call for standardised meta-information practices as a crucial step for proper machine learning solutions development, validation, and data sharing. Such practices include detailing the dataset generation process, aiming for automatic integration of causal relationships.
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Garcia Santa Cruz, Beatriz ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Vega Moreno, Carlos Gonzalo ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core
Hertel, Frank ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC)
External co-authors :
no
Language :
English
Title :
The need of standardised metadata to encode causal relationships: Towards safer data-driven machine learning biological solutions
Publication date :
16 November 2021
Number of pages :
6
Event name :
Computational Intelligence Methods for Bioinformatics and Biostatistics 2021
Event date :
from 14-10-2021 to 16-10-2021
Audience :
International
Focus Area :
Systems Biomedicine
Available on ORBilu :
since 12 December 2021

Statistics


Number of views
113 (18 by Unilu)
Number of downloads
0 (0 by Unilu)

Bibliography


Similar publications



Contact ORBilu