GradTree: Learning axis-aligned decision trees with gradient descent

Marton, Sascha ; Lüdtke, Stefan ; Bartelt, Christian ; Stuckenschmidt, Heiner

Document Type: Conference or workshop publication
Year of publication: 2024
Book title: Proceedings of the 38th AAAI Conference on Artificial Intelligence
Volume: 38, No. 13
Page range: 14323-14331
Conference title: The 38th Annual AAAI Conference on Artificial Intelligence
Location of the conference venue: Vancouver, Canada
Date of the conference: 20.-27.02.2024
Publisher: Wooldridge, Michael ; Dy, Jennifer ; Natarajan, Sriraam
Place of publication: Washington, DC
Publishing house: AAAI Press
ISBN: 978-1-57735-887-9 , 1-57735-887-2
ISSN: 2159-5399
Related URLs:
Publication language: English
Institution: School of Business Informatics and Mathematics > Practical Computer Science II: Artificial Intelligence (Stuckenschmidt 2009-)
Außerfakultäre Einrichtungen > Institut für Enterprise Systems (InES)
Subject: 004 Computer science, internet
Keywords (English): decision trees , gradient descent , machine learning , Artificial Intelligence
Abstract: Decision Trees (DTs) are commonly used for many machine learning tasks due to their high degree of interpretability. However, learning a DT from data is a difficult optimization problem, as it is non-convex and non-differentiable. Therefore, common approaches learn DTs using a greedy growth algorithm that minimizes the impurity locally at each internal node. Unfortunately, this greedy procedure can lead to inaccurate trees. In this paper, we present a novel approach for learning hard, axis-aligned DTs with gradient descent. The proposed method uses backpropagation with a straight-through operator on a dense DT representation, to jointly optimize all tree parameters. Our approach outperforms existing methods on binary classification benchmarks and achieves competitive results for multi-class tasks. The implementation is available under:

Dieser Eintrag ist Teil der Universitätsbibliographie.

Metadata export


+ Search Authors in

+ Page Views

Hits per month over past year

Detailed information

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item