# Disentangled Representation for Causal Mediation Analysis

arXiv: https://arxiv.org/abs/2302.09694 · HTML: https://mlsanity.com/paper/2302.09694/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 19 Feb 2023.

## Builds on (most cited first, 6 of 6)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Pyro: Deep Universal Probabilistic Programming](https://mlsanity.com/paper/1810.09538/) (2018)
- [Treatment effect estimation with disentangled latent factors](https://mlsanity.com/paper/2001.10652/) (2020)
- [Causal Mediation Analysis with Hidden Confounders](https://mlsanity.com/paper/2102.11724/) (2021)
- [The Identification and Estimation of Direct and Indirect Effects in A/B Tests through Causal Mediation Analysis](https://mlsanity.com/paper/1906.09757/) (2019)

## Built on by (most cited first, 10 of 10)

- [Mitigating Propensity Bias of Large Language Models for Recommender Systems](https://mlsanity.com/paper/2409.20052/) (2024)
- [Causal Mediation Analysis with Multi-dimensional and Indirectly Observed Mediators](https://mlsanity.com/paper/2306.07918/) (2023)
- [Long-Term Individual Causal Effect Estimation via Identifiable Latent Representation Learning](https://mlsanity.com/paper/2505.05192/) (2025)
- [Fairness in Augmented Graph Learning: A Survey](https://mlsanity.com/paper/2504.21296/) (2025)
- [When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.09241/) (2026)
- [Causal Effect Estimation using identifiable Variational AutoEncoder with Latent Confounders and Post-Treatment Variables](https://mlsanity.com/paper/2408.07219/) (2024)
- [Causal Effect Estimation under Networked Interference without Networked Unconfoundedness Assumption](https://mlsanity.com/paper/2502.19741/) (2025)
- [MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation](https://mlsanity.com/paper/2603.25126/) (2026)
- [Leaning Time-Varying Instruments for Identifying Causal Effects in Time-Series Data](https://mlsanity.com/paper/2411.17774/) (2024)
- [The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining](https://mlsanity.com/paper/2609.32964/) (2026)

## Abstract (arXiv)

Estimating direct and indirect causal effects from observational data is crucial to understanding the causal mechanisms and predicting the behaviour under different interventions. Causal mediation analysis is a method that is often used to reveal direct and indirect effects. Deep learning shows promise in mediation analysis, but the current methods only assume latent confounders that affect treatment, mediator and outcome simultaneously, and fail to identify different types of latent confounders (e.g., confounders that only affect the mediator or outcome). Furthermore, current methods are based on the sequential ignorability assumption, which is not feasible for dealing with multiple types of latent confounders. This work aims to circumvent the sequential ignorability assumption and applies the piecemeal deconfounding assumption as an alternative. We propose the Disentangled Mediation Analysis Variational AutoEncoder (DMAVAE), which disentangles the representations of latent confounders into three types to accurately estimate the natural direct effect, natural indirect effect and total effect. Experimental results show that the proposed method outperforms existing methods and has strong generalisation ability. We further apply the method to a real-world dataset to show its potential application.