DNet: distributional network for distributional individualized treatment effects

Wu, Guojun, Song, Ge, Lv, Xiaoxiang, Luo, Shikai, Shi, Chengchun ORCID: 0000-0001-7773-2099 and Zhu, Hongtu (2023) DNet: distributional network for distributional individualized treatment effects. Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 5215 - 5224. ISSN 2154-817X

Text (Distributional Network for Distributional Individualized Treatment Effects) - Published Version Available under License Other license. Download (661kB)

• Scopus publication

Abstract

There is a growing interest in developing methods to estimate individualized treatment effects (ITEs) for various real-world applications, such as e-commerce and public health. This paper presents a novel architecture, called DNet, to infer distributional ITEs. DNet can learn the entire outcome distribution for each treatment, whereas most existing methods primarily focus on the conditional average treatment effect and ignore the conditional variance around its expectation. Additionally, our method excels in settings with heavy-tailed outcomes and outperforms state-of-the-art methods in extensive experiments on benchmark and real-world datasets. DNet has also been successfully deployed in a widely used mobile app with millions of daily active users.

Item Type:	Article
Additional Information:	© The Authors | ACM 2023. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in 2023 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, http://dx.doi.org/10.1145/3580305.3599809
Divisions:	Statistics
Date Deposited:	03 May 2024 11:48
Last Modified:	29 Nov 2024 01:49
URI:	http://eprints.lse.ac.uk/id/eprint/122895

Actions (login required)

View Item