Enabling mixed effects neural networks for diverse, clustered data using Monte Carlo methods

Tschalzev, Andrej ; Nitschke, Paul ; Kirchdorfer, Lukas ; Lüdtke, Stefan ; Bartelt, Christian ; Stuckenschmidt, Heiner

Document Type: Conference or workshop publication
Year of publication: 2024
Book title: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence: Jeju, 03-09 August 2024
Volume: tba
Page range: tba
Conference title: IJCAI 2024, 33rd International Joint Conference on Artificial Intelligence
Location of the conference venue: Jeju, South Korea
Date of the conference: 03.-09.08.2024
Place of publication: Jeju, South Korea
Publishing house: International Joint Conferences on Artificial Intelligence
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): machine learning , artificial intelligence , deep learning
Abstract: Neural networks often assume independence among input data samples, disregarding correlations arising from inherent clustering patterns in real-world datasets (e.g., due to different sites or repeated measurements). Recently, mixed effects neural networks (MENNs) which separate cluster-specific 'random effects' from cluster-invariant 'fixed effects' have been proposed to improve generalization and interpretability for clustered data. However, existing methods only allow for approximate quantification of cluster effects and are limited to regression and binary targets with only one clustering feature. We present MC-GMENN, a novel approach employing Monte Carlo methods to train Generalized Mixed Effects Neural Networks. We empirically demonstrate that MC-GMENN outperforms existing mixed effects deep learning models in terms of generalization performance, time complexity, and quantification of inter-cluster variance. Additionally, MC-GMENN is applicable to a wide range of datasets, including multi-class classification tasks with multiple high-cardinality categorical features. For these datasets, we show that MC-GMENN outperforms conventional encoding and embedding methods, simultaneously offering a principled methodology for interpreting the effects of clustering patterns.

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