NodeFlow: Towards End-to-End Flexible Probabilistic Regression on Tabular Data
Entropy · 11.07.2024 · 26 (7) · 593
DOI: 10.3390/e26070593 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 11.07.2024. Verfasst von Patryk Wielopolski und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence, Wrocław University of Science and Technology, 50-370 Wrocław, Poland. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Polish Grid Infrastructure, National Science Center, National Centre of Science (Poland).
Abstract (Originalsprache)
We introduce NodeFlow, a flexible framework for probabilistic regression on tabular data that combines Neural Oblivious Decision Ensembles (NODEs) and Conditional Continuous Normalizing Flows (CNFs). It offers improved modeling capabilities for arbitrary probabilistic distributions, addressing the limitations of traditional parametric approaches. In NodeFlow, the NODE captures complex relationships in tabular data through a tree-like structure, while the conditional CNF utilizes the NODE’s output space as a conditioning factor. The training process of NodeFlow employs standard gradient-based learning, facilitating the end-to-end optimization of the NODEs and CNF-based density estimation. This approach ensures outstanding performance, ease of implementation, and scalability, making NodeFlow an appealing choice for practitioners and researchers. Comprehensive assessments on benchmark datasets underscore NodeFlow’s efficacy, revealing its achievement of state-of-the-art outcomes in multivariate probabilistic regression setup and its strong performance in univariate regression tasks. Furthermore, ablation studies are conducted to justify the design choices of NodeFlow. In conclusion, NodeFlow’s end-to-end training process and strong performance make it a compelling solution for practitioners and researchers. Additionally, it opens new avenues for research and application in the field of probabilistic regression on tabular data.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Artificial Intelligence, Wrocław University of Science and Technology, 50-370 Wrocław, Poland.
- Tooploox Ltd., 53-601 Wrocław, Poland.
ORCID-Profile: Patryk Wielopolski, Maciej Zięba
Förderung
- Polish Grid Infrastructure
- National Science Center
- National Centre of Science (Poland)
- Polish high-performance computing infrastructure PLGrid (HPC Center: ACK Cyfronet AGH) for providing computer facilities and support within computational
Zitieren
APA
Wielopolski, P., Furman, O., & Zięba, M. (2024). NodeFlow: Towards End-to-End Flexible Probabilistic Regression on Tabular Data. Entropy, 26(7), 593. https://doi.org/10.3390/e26070593
Vancouver
Wielopolski P, Furman O, Zięba M. NodeFlow: Towards End-to-End Flexible Probabilistic Regression on Tabular Data. Entropy. 2024;26(7):593. doi:10.3390/e26070593
BibTeX
@article{Wielopolski2024,
author = {Wielopolski, Patryk and Furman, Oleksii and Zięba, Maciej},
title = {NodeFlow: Towards End-to-End Flexible Probabilistic Regression on Tabular Data},
journal = {Entropy},
year = {2024},
volume = {26},
number = {7},
pages = {593},
doi = {10.3390/e26070593}
}
EUVIMED