mlsanityData to 14 Oct 2026

Proximity Matters: Local Proximity Enhanced Balancing for Treatment Effect Estimation

arXiv 2407.01111 ↗First posted 1 Jul 2024cs.LG cs.AI stat.MLcited by 7

Not on the map. Why?

Abstract (arXiv)

Heterogeneous treatment effect (HTE) estimation from observational data poses significant challenges due to treatment selection bias. Existing methods address this bias by minimizing distribution discrepancies between treatment groups in latent space, focusing on global alignment. However, the fruitful aspect of local proximity, where similar units exhibit similar outcomes, is often overlooked. In this study, we propose Proximity-enhanced CounterFactual Regression (CFR-Pro) to exploit proximity for enhancing representation balancing within the HTE estimation context. Specifically, we introduce a pair-wise proximity regularizer based on optimal transport to incorporate the local proximity in discrepancy calculation. However, the curse of dimensionality renders the proximity measure and discrepancy estimation ineffective -- exacerbated by limited data availability for HTE estimation. To handle this problem, we further develop an informative subspace projector, which trades off minimal distance precision for improved sample complexity. Extensive experiments demonstrate that CFR-Pro accurately matches units across different treatment groups, effectively mitigates treatment selection bias, and significantly outperforms competitors. Code is available at https://github.com/HowardZJU/CFR-Pro.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 24 of its 61 references that are in the map. First posted on arXiv 1 Jul 2024.

Builds on

24 of 61 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  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. 2015Optimal Transport for Domain Adaptationcited by 463
  5. 2016Learning Representations for Counterfactual Inferencecited by 329
  6. 2019Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matchingcited by 103
  7. 2018Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical propertiescited by 93
  8. 2019Learning Counterfactual Representations for Estimating Individual Dose-Response Curvescited by 90
  9. 2020Faster Wasserstein Distance Estimation with the Sinkhorn Divergencecited by 73
  10. 2021AutoDebias: Learning to Debias for Recommendationcited by 68
  11. 2022ESCM2: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimationcited by 47
  12. 2020Projection Robust Wasserstein Distance and Riemannian Optimizationcited by 45
12 more
  1. 2019Large-scale Causal Approaches to Debiasing Post-click Conversion Rate Estimation with Multi-task Learningcited by 39
  2. 2021Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimationcited by 28
  3. 2022On the Opportunity of Causal Learning in Recommendation Systems: Foundation, Estimation, Prediction and Challengescited by 28
  4. 2022Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimizationcited by 19
  5. 2022A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Predictioncited by 18
  6. 2023Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendationscited by 18
  7. 2022DESCN: Deep Entire Space Cross Networks for Individual Treatment Effect Estimationcited by 16
  8. 2016Local Similarity-Aware Deep Feature Embeddingcited by 15
  9. 2022Entire Space Counterfactual Learning for Reliable Content Recommendationscited by 13
  10. 2021Optimal transport weights for causal inferencecited by 7
  11. 2021Deep Treatment-Adaptive Network for Causal Inferencecited by 5
  12. 2024Revisiting Counterfactual Regression through the Lens of Gromov-Wasserstein Information Bottleneckcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025Time-o1: Time-Series Forecasting Needs Transformed Label Alignmentcited by 22
  2. 2025DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignmentcited by 13
  3. 2025Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Modelscited by 10
  4. 2026CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbackscited by 7
  5. 2025Learning Counterfactual Outcomes Under Rank Preservationcited by 0
  6. 2026Deep Time-Series Forecasting in 10 Years: A Surveycited by 0
  7. 2026Disentangled Double Machine Learning for Accurate Causal Effect Estimationcited by 0