Conference paper Open Access

The need of standardised metadata to encode causal relationships: Towards safer data-driven machine learning biological solutions

Beatriz Garcia Santa Cruz; Carlos Vega; Frank Hertel


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">confounders</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">causality</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">metadata</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">machine learning</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">systems biology</subfield>
  </datafield>
  <controlfield tag="005">20211126134842.0</controlfield>
  <controlfield tag="001">5729350</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="0">(orcid)0000-0002-7979-9921</subfield>
    <subfield code="a">Carlos Vega</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Frank Hertel</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">360296</subfield>
    <subfield code="z">md5:e79ab151c2eae88041ddf91b58ca231d</subfield>
    <subfield code="u">https://zenodo.org/record/5729350/files/Authors__guidelines_for_CIBB_short_papers (1).pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-11-16</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:5729350</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="0">(orcid)0000-0002-0939-4443</subfield>
    <subfield code="a">Beatriz Garcia Santa Cruz</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">The need of standardised metadata to encode causal relationships: Towards safer data-driven machine learning biological solutions</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;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.&amp;nbsp;&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.5729349</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.5729350</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
94
52
views
downloads
All versions This version
Views 9494
Downloads 5252
Data volume 18.7 MB18.7 MB
Unique views 7676
Unique downloads 4141

Share

Cite as