An Out-of-Distribution Generalization Framework Based on Variational Backdoor Adjustment

Hang Su () and Wei Wang
Additional contact information
Hang Su: School of Mathematics, Renmin University of China, Beijing 100872, China
Wei Wang: School of Mathematics, Renmin University of China, Beijing 100872, China

Mathematics, 2023, vol. 12, issue 1, 1-21

Abstract: In practical applications, learning models that can perform well even when the data distribution is different from the training set are essential and meaningful. Such problems are often referred to as out-of-distribution (OOD) generalization problems. In this paper, we propose a method for OOD generalization based on causal inference. Unlike the prevalent OOD generalization methods, our approach does not require the environment labels associated with the data in the training set. We analyze the causes of distributional shifts in data from a causal modeling perspective and then propose a backdoor adjustment method based on variational inference. Finally, we constructed a unique network structure to simulate the variational inference process. The proposed variational backdoor adjustment (VBA) framework can be combined with any mainstream backbone network. In addition to theoretical derivation, we conduct experiments on different datasets to demonstrate that our method performs well in prediction accuracy and generalization gaps. Furthermore, by comparing the VBA framework with other mainstream OOD methods, we show that VBA performs better than mainstream methods.

Keywords: out-of-distribution generalization; causal inference; machine learning; backdoor adjustment; supervised learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/1/85/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/1/85/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2023:i:1:p:85-:d:1307816

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().