# Disentangled Instrumental Variables for Causal Inference with Networked Observational Data

arXiv: https://arxiv.org/abs/2602.07765 · HTML: https://mlsanity.com/paper/2602.07765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 38 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Builds on (most cited first, 18 of 18)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Adapting Neural Networks for the Estimation of Treatment Effects](https://mlsanity.com/paper/1906.02120/) (2019)
- [β-Variational autoencoders and transformers for reduced-order modelling of fluid flows](https://mlsanity.com/paper/2304.03571/) (2023)
- [Estimating Treatment Effects with Causal Forests: An Application](https://mlsanity.com/paper/1902.07409/) (2019)
- [Learning Individual Causal Effects from Networked Observational Data](https://mlsanity.com/paper/1906.03485/) (2019)
- [Learning Causal Effects on Hypergraphs](https://mlsanity.com/paper/2207.04049/) (2022)
- [Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition](https://mlsanity.com/paper/2107.05884/) (2021)
- [Doubly Robust Causal Effect Estimation under Networked Interference via Targeted Learning](https://mlsanity.com/paper/2405.03342/) (2024)
- [Learning Individual Treatment Effects under Heterogeneous Interference in Networks](https://mlsanity.com/paper/2210.14080/) (2022)
- [Generalization bound for estimating causal effects from observational network data](https://mlsanity.com/paper/2308.04011/) (2023)
- [Instrumental Variables in Causal Inference and Machine Learning: A Survey](https://mlsanity.com/paper/2212.05778/) (2022)
- [Instrumental Variable Estimation for Causal Inference in Longitudinal Data with Time-Dependent Latent Confounders](https://mlsanity.com/paper/2312.07175/) (2023)
- [Conditional Instrumental Variable Regression with Representation Learning for Causal Inference](https://mlsanity.com/paper/2310.01865/) (2023)
- [Discovering Ancestral Instrumental Variables for Causal Inference from Observational Data](https://mlsanity.com/paper/2206.01931/) (2022)
- [A Look into Causal Effects under Entangled Treatment in Graphs: Investigating the Impact of Contact on MRSA Infection](https://mlsanity.com/paper/2307.08237/) (2023)
- [Treatment-Aware Hyperbolic Representation Learning for Causal Effect Estimation with Social Networks](https://mlsanity.com/paper/2401.06557/) (2024)
- [Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems](https://mlsanity.com/paper/2408.09651/) (2024)

## Abstract (arXiv)

Instrumental variables (IVs) are crucial for addressing unobservable confounders, yet their stringent exogeneity assumptions pose significant challenges in networked data. Existing methods typically rely on modelling neighbour information when recovering IVs, thereby inevitably mixing shared environment-induced endogenous correlations and individual-specific exogenous variation, leading the resulting IVs to inherit dependence on unobserved confounders and to violate exogeneity. To overcome this challenge, we propose underlineDisentangled underlineInstrumental underlineVariables (DisIV) framework, a novel method for causal inference based on networked observational data with latent confounders. DisIV exploits network homogeneity as an inductive bias and employs a structural disentanglement mechanism to extract individual-specific components that serve as latent IVs. The causal validity of the extracted IVs is constrained through explicit orthogonality and exclusion conditions. Extensive semi-synthetic experiments on real-world datasets demonstrate that DisIV consistently outperforms state-of-the-art baselines in causal effect estimation under network-induced confounding.