Research Overview
My research explores the intersection of causal inference and machine learning to build robust, explainable, and fair AI systems. Our work is frequently published in top AI/ML venues such as NeurIPS, ICML, AAAI, UAI, and AISTATS.
[Google Scholar], [Openreview Profile]
Our core research themes include:
- Identifiability & Transportability ID TR : Generalizing causal effect estimations across heterogeneous environments.
- Causal Decision-Making DM : Utilizing causality as a first principle to optimize actions under uncertainty.
- Causal Machine Learning CML : Developing causal representation learning and causality-inspired AI models.
- Causal Discovery CD REL : Recovering underlying causal graphs from complex, observational, or relational data.
Preprints
DM
On Transportability for Structural Causal Bandits [preprint]
Min Woo Park, Sanghack Lee
CML Towards Causal Representation Learning with Observable Sources as Auxiliaries [preprint]
Kwonho Kim, Heejeong Nam, Inwoo Hwang, Sanghack Lee*
DM
An Introduction to Causal Reinforcement Learning [preprint]
Elias Bareinboim, Junzhe Zhang, Sanghack Lee
Published Papers
* for joint first authorship or corresponding author
2026
DM Counterfactual Structural Causal Bandits
Min Woo Park, Sanghack Lee*
ICLR 2026 (to appear)
CML Mitigating Length Bias in RLHF through a Causal Lens [arXiv]
Hyeonji Kim, Sujeong Oh, Sanghack Lee*
AAAI 2026
2025
DM
Structural Causal Bandits under Markov Equivalence [paper]
Min Woo Park, Andy Arditi, Elias Bareinboim*, Sanghack Lee*
NeurIPS 2025
DM
Non-Stationary Structural Causal Bandits [paper]
Yeahoon Kwon, Yesong Choe, Soungmin Park, Neil Dhir*, Sanghack Lee*
NeurIPS 2025
CML On Predicting Post-Click Conversion Rate via Counterfactual Inference [arXiv]
Junhyung Ahn, Sanghack Lee*
ICDM 2025 (Best Paper Award Finalist)
CML PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization [paper]
Dong Kyu Cho, Inwoo Hwang, Sanghack Lee*
CVPR 2025
2024
DM
Toward a Complete Criterion for Value of Information in Insoluble Decision Problems [paper]
Ryan Carey, Sanghack Lee, Robin J. Evans
Transactions on Machine Learning 2024
ID Complete Graphical Criterion for Sequential Covariate Adjustment in Causal Inference [paper]
Yonghan Jung, Min Woo Park, Sanghack Lee*
NeurIPS 2024
CD
DM
CML Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning [paper], [poster]
Inwoo Hwang, Yunhyeok Kwak, Suhyung Choi, Byoung-Tak Zhang*, Sanghack Lee*
ICML 2024 (previously, GenPlan workshop at NeurIPS 2023, SCIS workshop at ICML 2023)
ID On Positivity Condition for Causal Inference [paper], [poster]
Inwoo Hwang*, Yesong Choe*, Yeahoon Kwon, Sanghack Lee*
ICML 2024 (+ Causality workshop at UAI 2024)
CD
DM
Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction [paper]
Yunhyeok Kwak*, Inwoo Hwang*, Dooyoung Kim, Sanghack Lee*, Byoung-Tak Zhang*
UAI 2024, Oral
CD Causal Discovery with Deductive Reasoning: One Less Problem [paper], [poster]
Jonghwan Kim, Inwoo Hwang, Sanghack Lee*
UAI 2024
CD Filter, Rank, and Prune: Learning Linear Cyclic Gaussian Graphical Models [paper]
Soheun Yi, Sanghack Lee*
AISTATS 2024
2023
CD
CML On Discovery of Local Independence over Continuous Variables via Neural Contextual Decomposition [paper]
Inwoo Hwang, Yunhyeok Kwak, Yeon-Ji Song, Byoung-Tak Zhang*, Sanghack Lee*
CLeaR 2023
2022
TR Counterfactual Transportability: A Formal Approach [paper]
Juan D. Correa, Sanghack Lee and Elias Bareinboim
ICML 2022
2021
ID Nested Counterfactual Identification from Arbitrary Surrogate Experiments [paper]
Juan D. Correa, Sanghack Lee and Elias Bareinboim
NeurIPS 2021
ID Causal Identification with Matrix Equations [paper]
Sanghack Lee and Elias Bareinboim
NeurIPS 2021, Oral
Workshops
ws
ID
CML Instrumental Variable Representation Learning under Confounded Covariates
Jungsoo Kim, Kwonho Kim, Inwoo Hwang, Sanghack Lee*
NeurIPS 2025 Workshop: CauScien—Uncovering Causality in Science
ws
CMLTowards Causal Representation Learning with Observable Sources as Auxiliaries
Kwonho Kim, Heejeong Nam, Inwoo Hwang, Sanghack Lee*
ICML 2025 Workshop on Scaling Up Intervention Models & UAI 2025 Workshop on Causal Abstractions and Representations
ws
ML Locality-aware Concept Bottleneck Model
Sujin Jeon, Inwoo Hwang, Sanghack Lee*, Byoung-Tak Zhang*
UniReps: 2nd Edition of the Workshop on Unifying Representations in Neural Models at NeurIPS 2024
ws
CML Learning to ignore: Single Source Domain Generalization via Oracle Regularization [paper]
Dong Kyu Cho, Sanghack Lee*
Causal Representation Learning Workshop at NeurIPS 2023
ws
CD
Partition-based Local Independence Discovery
Inwoo Hwang, Byoung-Tak Zhang, and Sanghack Lee
Causal Inference Challenges in Sequential Decision Making: Bridging Theory and Practice Worksop at NeurIPS 2021
before 2020
DM Characterizing Optimal Mixed Policies: Where to Intervene and What to Observe [paper], [slides], [poster]
Sanghack Lee and Elias Bareinboim
NeurIPS 2020
ID Causal Effect Identifiability under Partial-Observability [paper]
Sanghack Lee, and Elias Bareinboim
ICML 2020
TR General Transportability — Synthesizing Experiments from Heterogeneous Domains [paper]
Sanghack Lee, Juan D. Correa, and Elias Bareinboim
AAAI 2020
ID Identifiability from a Combination of Observations and Experiments [paper], [slides]
Sanghack Lee, Juan D. Correa, and Elias Bareinboim
AAAI 2020
ID General Identifiability with Arbitrary Surrogate Experiments [paper] [errata]
Sanghack Lee, Juan D. Correa, and Elias Bareinboim
UAI 2019, Best Paper Award
CD REL Towards Robust Relational Causal Discovery [paper]
Sanghack Lee and Vasant Honavar
UAI 2019
DM Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality [paper]
Aria Khademi, Sanghack Lee, David Foley, and Vasant Honavar
WWW 2019
DM On Structural Causal Bandit with Non-manipulable Variables [paper], [poster], [slides]
Sanghack Lee and Elias Bareinboim
AAAI 2019, Oral
DM Structural Causal Bandits: Where to Intervene? [paper], [code], [poster]
Sanghack Lee and Elias Bareinboim
NeurIPS 2018
CD CIT REL A Kernel Conditional Independence Test for Relational Data [code], [paper]
Sanghack Lee and Vasant Honavar
UAI 2017
CIT Self-Discrepancy Conditional Independence Test [code], [paper]
Sanghack Lee and Vasant Honavar
UAI 2017
CD REL A Characterization of Markov Equivalence Classes for Relational Causal Model with Path Semantics [code], [paper], [appendix]
Sanghack Lee and Vasant Honavar
UAI 2016, Oral
CD REL On Learning Causal Models from Relational Data [code] [paper]
Sanghack Lee and Vasant Honavar
AAAI 2016, Oral
“Teens are from Mars, Adults are from Venus”: Analyzing and Predicting Age Groups with Behavioral Characteristics in Instagram [paper]
Kyungsik Han, Sanghack Lee, Jin Yea Jang, Yong Jung, and Dongwon Lee
WebSci 2016
ws
CD REL Lifted Representation of Relational Causal Models Revisited: Implications for Reasoning and Structure Learning [paper]
Sanghack Lee and Vasant Honavar
UAI 2015 Workshop on Advances in Causal Inference
TR Transportability from Multiple Environments with Limited Experiments [paper]
Elias Bareinboim*, Sanghack Lee*, Vasant Honavar, and Judea Pearl
NeurIPS 2013
TR Causal Transportability of Experiments on Controllable Subsets of Variables: z-Transportability [paper]
Sanghack Lee and Vasant Honavar
UAI 2013
TR m-Transportability: Transportability of a Causal Effect from Multiple Environments
Sanghack Lee and Vasant Honavar
AAAI 2013
ML Learning Classifiers from Distributional Data
Harris Lin*, Sanghack Lee*, Ngot Bui*, and Vasant Honavar
IEEE International Congress on Big Data