Disentangled Representation Learning for Causal Inference with Instruments
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916509968760832 |
|---|---|
| author | Cheng, Debo Li, Jiuyong Liu, Lin Xu, Ziqi Zhang, Weijia Liu, Jixue Le, Thuc Duy |
| author_facet | Cheng, Debo Li, Jiuyong Liu, Lin Xu, Ziqi Zhang, Weijia Liu, Jixue Le, Thuc Duy |
| contents | Latent confounders are a fundamental challenge for inferring causal effects from observational data. The instrumental variable (IV) approach is a practical way to address this challenge. Existing IV based estimators need a known IV or other strong assumptions, such as the existence of two or more IVs in the system, which limits the application of the IV approach. In this paper, we consider a relaxed requirement, which assumes there is an IV proxy in the system without knowing which variable is the proxy. We propose a Variational AutoEncoder (VAE) based disentangled representation learning method to learn an IV representation from a dataset with latent confounders and then utilise the IV representation to obtain an unbiased estimation of the causal effect from the data. Extensive experiments on synthetic and real-world data have demonstrated that the proposed algorithm outperforms the existing IV based estimators and VAE-based estimators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04641 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Disentangled Representation Learning for Causal Inference with Instruments Cheng, Debo Li, Jiuyong Liu, Lin Xu, Ziqi Zhang, Weijia Liu, Jixue Le, Thuc Duy Machine Learning Artificial Intelligence Latent confounders are a fundamental challenge for inferring causal effects from observational data. The instrumental variable (IV) approach is a practical way to address this challenge. Existing IV based estimators need a known IV or other strong assumptions, such as the existence of two or more IVs in the system, which limits the application of the IV approach. In this paper, we consider a relaxed requirement, which assumes there is an IV proxy in the system without knowing which variable is the proxy. We propose a Variational AutoEncoder (VAE) based disentangled representation learning method to learn an IV representation from a dataset with latent confounders and then utilise the IV representation to obtain an unbiased estimation of the causal effect from the data. Extensive experiments on synthetic and real-world data have demonstrated that the proposed algorithm outperforms the existing IV based estimators and VAE-based estimators. |
| title | Disentangled Representation Learning for Causal Inference with Instruments |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.04641 |