Propensity Score

Propensity score methods are statistical techniques used to estimate causal effects from observational data by adjusting for confounding variables—factors that influence both treatment assignment and the outcome of interest. Current research emphasizes improving the robustness and accuracy of propensity score estimation, particularly focusing on doubly robust estimators, inverse probability weighting, and methods that incorporate uncertainty quantification and calibration. These advancements are crucial for reliable causal inference across diverse fields, ranging from healthcare and economics to online advertising and social media analysis, enabling more accurate evaluation of interventions and policies.

Papers

November 9, 2023

Generalized test utilities for long-tail performance in extreme multi-label classification
Erik Schultheis, Marek Wydmuch, Wojciech Kotłowski, Rohit Babbar, Krzysztof Dembczyński
Multi Label Classification Long Tail Propensity Score Extreme Multi Label Utility Function Tail Label

October 24, 2023

Causal Understanding of Why Users Share Hate Speech on Social Media
Dominique Geissler, Abdurahman Maarouf, Stefan Feuerriegel
Social Medium Causal Inference Hate Speech User Base Social Medium Data Propensity Score Causal Interpretation

October 12, 2023

When Machine Learning Models Leak: An Exploration of Synthetic Training Data
Manel Slokom, Peter-Paul de Wolf, Martha Larson
Machine Learning Model Synthetic Data Environment Exploration Synthetic Training Data Sensitive Attribute Propensity Score Training Data Leakage

October 10, 2023

Positivity-free Policy Learning with Observational Data
Pan Zhao, Antoine Chambaz, Julie Josse, Shu Yang
Modeling Assumption Observational Data Propensity Score Treatment Assignment

September 8, 2023

Offline Recommender System Evaluation under Unobserved Confounding
Olivier Jeunen, Ben London
Policy Evaluation Modeling Assumption Unobserved Confounders Propensity Score Policy Estimation Unmeasured Confounding Offline Evaluation

August 24, 2023

Machine Unlearning for Causal Inference
Vikas Ramachandra, Mohit Sethi
Causal Inference Machine Unlearning Causal Analysis Propensity Score

August 15, 2023

Semi-Supervised Learning with Multiple Imputations on Non-Random Missing Labels
Jason Lu, Michael Ma, Huaze Xu, Zixi Xu
Semi Supervised Learning Propensity Score Missing Label Deep Imputation Multiple Imputation

August 8, 2023

Generalization bound for estimating causal effects from observational network data
Ruichu Cai, Zeqin Yang, Weilin Chen, Yuguang Yan, Zhifeng Hao
Strong Generalization Causal Inference Causal Effect Causal Effect Estimation Propensity Score

June 1, 2023

Calibrated and Conformal Propensity Scores for Causal Effect Estimation
Shachi Deshpande, Volodymyr Kuleshov
Causal Effect Estimation Propensity Score Inverse Propensity Weighting Global Calibration

May 23, 2023

Covariate balancing using the integral probability metric for causal inference
Insung Kong, Yuha Park, Joonhyuk Jung, Kwonsang Lee, Yongdai Kim
Causal Inference Relevant Covariates Propensity Score ApeRIodic SEmi Parametric Optimal Weight

April 6, 2023

Modelling customer lifetime-value in the retail banking industry
Greig Cowan, Salvatore Mercuri, Raad Khraishi
Long Term Cooperation Propensity Score Customer Lifetime Value

March 23, 2023

Uncertainty Calibration for Counterfactual Propensity Estimation in Recommendation
Wenbo Hu, Xin Sun, Qiang liu, Shu Wu
Effective Recommendation Uncertainty Calibration Propensity Score Inverse Propensity

January 22, 2023

Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers
Khalil Damak, Sami Khenissi, Olfa Nasraoui
Sequential Recommendation Propensity Score Bidirectional Transformer Representational Capacity Cloze Style

December 22, 2022

Cross-Dataset Propensity Estimation for Debiasing Recommender Systems
Fengyu Li, Sarah Dean
Recommender System Causal Inference Movie Recommendation Propensity Score Selection Bias Debiased Recommendation Inverse Probability Weighting

October 4, 2022

Time-Varying Propensity Score to Bridge the Gap between the Past and Present
Rasool Fakoor, Jonas Mueller, Zachary C. Lipton, Pratik Chaudhari, Alexander J. Smola
Speech Presence Propensity Score Railway BRIDGE Member Reinforcement Learning Task Data Shift

September 16, 2022

Double logistic regression approach to biased positive-unlabeled data
Konrad Furmańczyk, Jan Mielniczuk, Wojciech Rejchel, Paweł Teisseyre
Logistic Regression Propensity Score Unlabeled Learning Joint Inference Joint Estimation Positive Unlabeled Data

August 5, 2022

Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss
Junjie Wang, Yuxiang Zhang, Ping Yang, Ruyi Gan
Pre Trained Language Model Semantic Relation Propensity Score Masked Language Modeling

July 26, 2022

On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification
Erik Schultheis, Marek Wydmuch, Rohit Babbar, Krzysztof Dembczyński
Recommender System Long Tailed Propensity Score Missing Label Extreme Multi Label Tail Label

June 29, 2022

On Non-Random Missing Labels in Semi-Supervised Learning
Xinting Hu, Yulei Niu, Chunyan Miao, Xian-Sheng Hua, Hanwang Zhang
Semi Supervised Learning Pseudo Label Propensity Score Label Bias Missing Label Deep Imputation

June 13, 2022

Estimating Causal Effects Under Image Confounding Bias with an Application to Poverty in Africa
Connor T. Jerzak, Fredrik Johansson, Adel Daoud
Application Proficiency Causal Inference Causal Effect Causal Effect Estimation Observational Data Propensity Score Observational Study Poverty Level Biased Causal Effect