mlsanityData to 14 Oct 2026

PairNet: Training with Observed Pairs to Estimate Individual Treatment Effect

arXiv 2406.03864 ↗First posted 6 Jun 2024cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Given a dataset of individuals each described by a covariate vector, a treatment, and an observed outcome on the treatment, the goal of the individual treatment effect (ITE) estimation task is to predict outcome changes resulting from a change in treatment. A fundamental challenge is that in the observational data, a covariate's outcome is observed only under one treatment, whereas we need to infer the difference in outcomes under two different treatments. Several existing approaches address this issue through training with inferred pseudo-outcomes, but their success relies on the quality of these pseudo-outcomes. We propose PairNet, a novel ITE estimation training strategy that minimizes losses over pairs of examples based on their factual observed outcomes. Theoretical analysis for binary treatments reveals that PairNet is a consistent estimator of ITE risk, and achieves smaller generalization error than baseline models. Empirical comparison with thirteen existing methods across eight benchmarks, covering both discrete and continuous treatments, shows that PairNet achieves significantly lower ITE error compared to the baselines. Also, it is model-agnostic and easy to implement.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 23 of its 45 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

23 of 45 references.

References · 23

  1. 2017Billion-scale similarity search with GPUscited by 2,497
  2. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 600
  3. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
  4. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
  5. 2017Quasi-Oracle Estimation of Heterogeneous Treatment Effectscited by 332
  6. 2016Learning Representations for Counterfactual Inferencecited by 329
  7. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 287
  8. 2017Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processescited by 158
  9. 2019Learning Counterfactual Representations for Estimating Individual Dose-Response Curvescited by 90
  10. 2020Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networkscited by 78
  11. 2021On Inductive Biases for Heterogeneous Treatment Effect Estimationcited by 75
  12. 2021VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatmentscited by 61
11 more
  1. 2018Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networkscited by 56
  2. 2018DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Trainingcited by 42
  3. 2023Optimal Transport for Treatment Effect Estimationcited by 32
  4. 2021A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Modelscited by 29
  5. 2023In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimationcited by 29
  6. 2022Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimationcited by 25
  7. 2018Adversarial Balancing for Causal Inferencecited by 10
  8. 2020Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effectscited by 9
  9. 2022Generalization bounds and algorithms for estimating conditional average treatment effect of dosagecited by 9
  10. 2022Adversarial De-confounding in Individualised Treatment Effects Estimationcited by 9
  11. 2024Continuous Treatment Effect Estimation Using Gradient Interpolation and Kernel Smoothingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2026Rank-Learner: Orthogonal Ranking of Treatment Effectscited by 3
  2. 2025Leveraging a Simulator for Learning Causal Representations from Post-Treatment Covariates for CATEcited by 0
  3. 2025PIPCFR: Pseudo-outcome Imputation with Post-treatment Variables for Individual Treatment Effect Estimationcited by 0