EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Missing data in amortized simulation-based neural posterior estimation

Zijian Wang iD, Jan Hasenauer, Yannik Schälte iD

PLOS Computational Biology · 2024

DOI: 10.1371/journal.pcbi.1012184 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2024. Verfasst von Zijian Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: University of Bonn, Life and Medical Sciences Institute, Bonn, Germany. Hauptthemen laut MEDLINE: Computer Simulation, Neural Networks, Computer, Computational Biology. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Federal Ministry of Education and Research (BMBF), German Research Foundation (DFG), German Ministry of Education and Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Amortized simulation-based neural posterior estimation provides a novel machine learning based approach for solving parameter estimation problems. It has been shown to be computationally efficient and able to handle complex models and data sets. Yet, the available approach cannot handle the in experimental studies ubiquitous case of missing data, and might provide incorrect posterior estimates. In this work, we discuss various ways of encoding missing data and integrate them into the training and inference process. We implement the approaches in the BayesFlow methodology, an amortized estimation framework based on invertible neural networks, and evaluate their performance on multiple test problems. We find that an approach in which the data vector is augmented with binary indicators of presence or absence of values performs the most robustly. Indeed, it improved the performance also for the simpler problem of data sets with variable length. Accordingly, we demonstrate that amortized simulation-based inference approaches are applicable even with missing data, and we provide a guideline for their handling, which is relevant for a broad spectrum of applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computer SimulationNeural Networks, ComputerComputational BiologyHumansMachine LearningBayes TheoremAlgorithmsData Interpretation, Statistical

Autor:innen und Institutionen

  • University of Bonn, Life and Medical Sciences Institute, Bonn, Germany.
  • Helmholtz Center Munich, Computational Health Center, Neuherberg, Germany.
  • Technical University Munich, Center for Mathematics, Garching, Germany.

ORCID-Profile: Zijian Wang, Yannik Schälte

Förderung

  • German Federal Ministry of Education and Research (BMBF)
  • German Research Foundation (DFG)
  • German Ministry of Education and Research
  • Deutsche Forschungsgemeinschaft
  • Joachim Herz Stiftung

Zitieren

APA

Wang, Z., Hasenauer, J., & Schälte, Y. (2024). Missing data in amortized simulation-based neural posterior estimation. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1012184

Vancouver

Wang Z, Hasenauer J, Schälte Y. Missing data in amortized simulation-based neural posterior estimation. PLOS Computational Biology. 2024. doi:10.1371/journal.pcbi.1012184

BibTeX
@article{Wang2024,
  author = {Wang, Zijian and Hasenauer, Jan and Schälte, Yannik},
  title = {Missing data in amortized simulation-based neural posterior estimation},
  journal = {PLOS Computational Biology},
  year = {2024},
  doi = {10.1371/journal.pcbi.1012184}
}
Kostenlos starten →