EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MonoNet: enhancing interpretability in neural networks via monotonic features

An-Phi Nguyen iD, Dana Lea Moreno, Nicolas Le-Bel, María Rodríguez Martínez iD

Bioinformatics Advances · 05.01.2023 · 3 (1)

DOI: 10.1093/bioadv/vbad016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics Advances, online erschienen am 23.02.2023. Verfasst von An-Phi Nguyen und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, ETH Zürich, Zürich 8092, Switzerland. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union’s Horizon 2020 research and innovation program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Being able to interpret and explain the predictions made by a machine learning model is of fundamental importance. Unfortunately, a trade-off between accuracy and interpretability is often observed. As a result, the interest in developing more transparent yet powerful models has grown considerably over the past few years. Interpretable models are especially needed in high-stake scenarios, such as computational biology and medical informatics, where erroneous or biased models’ predictions can have deleterious consequences for a patient. Furthermore, understanding the inner workings of a model can help increase the trust in the model. Results We introduce a novel structurally constrained neural network, MonoNet, which is more transparent, while still retaining the same learning capabilities of traditional neural models. MonoNet contains monotonically connected layers that ensure monotonic relationships between (high-level) features and outputs. We show how, by leveraging the monotonic constraint in conjunction with other post hoc strategies, we can interpret our model. To demonstrate our model’s capabilities, we train MonoNet to classify cellular populations in a single-cell proteomic dataset. We also demonstrate MonoNet’s performance in other benchmark datasets in different domains, including non-biological applications (in the Supplementary Material). Our experiments show how our model can achieve good performance, while providing at the same time useful biological insights about the most important biomarkers. We finally carry out an information-theoretical analysis to show how the monotonic constraint actively contributes to the learning process of the model. Availability and implementation Code and sample data are available at https://github.com/phineasng/mononet. Supplementary information Supplementary data are available at Bioinformatics Advances online.

Autor:innen und Institutionen

  • Department of Mathematics, ETH Zürich, Zürich 8092, Switzerland.
  • Cognitive Health Care and Life Sciences, IBM Research Europe, Zürich 8803, Switzerland.
  • Department of Mathematics, EPFL, 1015 Lausanne, Switzerland.
  • Department of Physics, ETH Zürich, Zürich 8092, Switzerland.

ORCID-Profile: An-Phi Nguyen, María Rodríguez Martínez

Förderung

  • European Union’s Horizon 2020 research and innovation program

Zitieren

APA

Nguyen, A. P., Moreno, D. L., Le-Bel, N., & Rodríguez Martínez, M. (2023). MonoNet: enhancing interpretability in neural networks via monotonic features. Bioinformatics Advances, 3(1). https://doi.org/10.1093/bioadv/vbad016

Vancouver

Nguyen AP, Moreno DL, Le-Bel N, Rodríguez Martínez M. MonoNet: enhancing interpretability in neural networks via monotonic features. Bioinformatics Advances. 2023;3(1). doi:10.1093/bioadv/vbad016

BibTeX
@article{Nguyen2023,
  author = {Nguyen, An-Phi and Moreno, Dana Lea and Le-Bel, Nicolas and Rodríguez Martínez, María},
  title = {MonoNet: enhancing interpretability in neural networks via monotonic features},
  journal = {Bioinformatics Advances},
  year = {2023},
  volume = {3},
  number = {1},
  doi = {10.1093/bioadv/vbad016}
}
Kostenlos starten →