Timezone: »

Counterfactual Transportability: A Formal Approach
Juan Correa · Sanghack Lee · Elias Bareinboim

Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #628

Generalizing causal knowledge across environments is a common challenge shared across many of the data-driven disciplines, including AI and ML. Experiments are usually performed in one environment (e.g., in a lab, on Earth, in a training ground), almost invariably, with the intent of being used elsewhere (e.g., outside the lab, on Mars, in the real world), in an environment that is related but somewhat different than the original one, where certain conditions and mechanisms are likely to change. This generalization task has been studied in the causal inference literature under the rubric of transportability (Pearl and Bareinboim, 2011). While most transportability works focused on generalizing associational and interventional distributions, the generalization of counterfactual distributions has not been formally studied. In this paper, we investigate the transportability of counterfactuals from an arbitrary combination of observational and experimental distributions coming from disparate domains. Specifically, we introduce a sufficient and necessary graphical condition and develop an efficient, sound, and complete algorithm for transporting counterfactual quantities across domains in nonparametric settings. Failure of the algorithm implies the impossibility of generalizing the target counterfactual from the available data without further assumptions.

Author Information

Juan Correa (Universidad Autónoma de Manizales)
Sanghack Lee (Seoul National University)
Sanghack Lee

I am an Assistant Professor in the Graduate School of Data Science at Seoul National University. Prior to joining Seoul National University, I was an Associate Research Scientist at Columbia University and Postdoctoral Research Associate at Computer Science, Purdue University working with Prof. Elias Bareinboim. I got my Ph.D. in College of Information Sciences and Technology, Pennsylvania State University, University Park, under the supervision of Prof. Vasant Honavar. Currently, I am working on developing methods for applying causality in sequential decision-making and developing theory of causal effect identifiability and transportability.

Elias Bareinboim (Columbia)
Elias Bareinboim

Elias Bareinboim is an associate professor in the Department of Computer Science and the director of the Causal Artificial Intelligence (CausalAI) Laboratory at Columbia University. His research focuses on causal and counterfactual inference and their applications to artificial intelligence and machine learning as well as data-driven fields in the health and social sciences. His work was the first to propose a general solution to the problem of ``causal data-fusion,'' providing practical methods for combining datasets generated under different experimental conditions and plagued with various biases. In the last years, Bareinboim has been exploring the intersection of causal inference with decision-making (including reinforcement learning) and explainability (including fairness analysis). Before joining Columbia, he was an assistant professor at Purdue University and received his Ph.D. in Computer Science from the University of California, Los Angeles. Bareinboim was named one of ``AI's 10 to Watch'' by IEEE, and is a recipient of an NSF CAREER Award, the Dan David Prize Scholarship, the 2014 AAAI Outstanding Paper Award, and the 2019 UAI Best Paper Award.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors