|
Decision trees that remember: Gradient-based learning of recurrent decision trees with memory
Marton, Sascha
;
Schneider, Moritz
;
Brinkmann, Jannik
;
Lüdtke, Stefan
;
Bartelt, Christian
;
Stuckenschmidt, Heiner
![[img]](https://madoc.bib.uni-mannheim.de/69507/1.hassmallThumbnailVersion/2_Decision_Trees_That_Remember.pdf)  Preview |
|
PDF
2_Decision_Trees_That_Remember.pdf
- Published
Download (2MB)
|
|
URL:
|
https://openreview.net/forum?id=u2Hh24rxW1¬eId=...
|
|
URN:
|
urn:nbn:de:bsz:180-madoc-695074
|
|
Document Type:
|
Conference or workshop publication
|
|
Year of publication:
|
2025
|
|
Book title:
|
The Thirteens International Conference on Learning Representations
|
|
Conference title:
|
New Frontiers in Associative Memory workshop at ICLR 2025
|
|
Location of the conference venue:
|
Singapore, Republic of Singapore
|
|
Date of the conference:
|
28.04.2025
|
|
Publishing house:
|
OpenReview.net
|
|
Related URLs:
|
|
|
Publication language:
|
English
|
|
Institution:
|
Außerfakultäre Einrichtungen > Institut für Enterprise Systems (InES)
School of Business Informatics and Mathematics > Practical Computer Science II: Artificial Intelligence (Stuckenschmidt 2009-)
|
|
Pre-existing license:
|
 Creative Commons Attribution 4.0 International (CC BY 4.0)
|
|
Subject:
|
004 Computer science, internet
|
|
Keywords (English):
|
decision tree , sequential data , time series data , recurrent decision tree
|
|
Abstract:
|
Neural architectures such as Recurrent Neural Networks (RNNs), Transformers, and State-Space Models have shown great success in handling sequential data by learning temporal dependencies. Decision Trees (DTs), on the other hand, remain a widely used class of models for structured tabular data but are typically not designed to capture sequential patterns directly. Instead, DT-based approaches for time-series data often rely on feature engineering, such as manually incorporating lag features, which can be suboptimal for capturing complex temporal dependencies. To address this limitation, we introduce ReMeDe Trees, a novel recurrent decision tree architecture that integrates an internal memory mechanism, similar to RNNs, to learn long-term dependencies in sequential data. Our model learns hard, axis-aligned decision rules for both output generation and state updates, optimizing them efficiently via gradient descent. We provide a proof-of-concept study on synthetic benchmarks to demonstrate the effectiveness of our approach.
|
 | Dieser Eintrag ist Teil der Universitätsbibliographie. |
 | Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt. |
 Search Authors in
BASE:
Marton, Sascha
;
Schneider, Moritz
;
Brinkmann, Jannik
;
Lüdtke, Stefan
;
Bartelt, Christian
;
Stuckenschmidt, Heiner
Google Scholar:
Marton, Sascha
;
Schneider, Moritz
;
Brinkmann, Jannik
;
Lüdtke, Stefan
;
Bartelt, Christian
;
Stuckenschmidt, Heiner
ORCID:
Marton, Sascha  ORCID: 0000-0001-8151-9223 ; Schneider, Moritz ; Brinkmann, Jannik ; Lüdtke, Stefan ; Bartelt, Christian ; Stuckenschmidt, Heiner ORCID: 0000-0002-0209-3859
You have found an error? Please let us know about your desired correction here: E-Mail
Actions (login required)
 |
Show item |
|
