mlsanityData to 7 Oct 2026

Disentangled Instrumental Variables for Causal Inference with Networked Observational Data

arXiv 2602.07765 ↗First posted 8 Feb 2026cs.AIcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 38 references that are in the map. First posted on arXiv 8 Feb 2026.

Builds on

18 of 38 references.

References · 18

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  3. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 285
  4. 2023β-Variational autoencoders and transformers for reduced-order modelling of fluid flowscited by 76
  5. 2019Estimating Treatment Effects with Causal Forests: An Applicationcited by 58
  6. 2019Learning Individual Causal Effects from Networked Observational Datacited by 56
  7. 2022Learning Causal Effects on Hypergraphscited by 31
  8. 2024Doubly Robust Causal Effect Estimation under Networked Interference via Targeted Learningcited by 19
  9. 2021Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decompositioncited by 18
  10. 2022Learning Individual Treatment Effects under Heterogeneous Interference in Networkscited by 11
  11. 2023Generalization bound for estimating causal effects from observational network datacited by 11
  12. 2022Instrumental Variables in Causal Inference and Machine Learning: A Surveycited by 10
6 more
  1. 2023Instrumental Variable Estimation for Causal Inference in Longitudinal Data with Time-Dependent Latent Confounderscited by 10
  2. 2023Conditional Instrumental Variable Regression with Representation Learning for Causal Inferencecited by 8
  3. 2022Discovering Ancestral Instrumental Variables for Causal Inference from Observational Datacited by 7
  4. 2023A Look into Causal Effects under Entangled Treatment in Graphs: Investigating the Impact of Contact on MRSA Infectioncited by 4
  5. 2024Treatment-Aware Hyperbolic Representation Learning for Causal Effect Estimation with Social Networkscited by 1
  6. 2024Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systemscited by 1

Built on by

Not cited yet.