2023-07-02-aloui23a.md

abstract	openreview	title	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
This work considers the problem of transferring causal knowledge between tasks for Individual Treatment Effect (ITE) estimation. To this end, we theoretically assess the feasibility of transferring ITE knowledge and present a practical framework for efficient transfer. A lower bound is introduced on the ITE error of the target task to demonstrate that ITE knowledge transfer is challenging due to the absence of counterfactual information. Nevertheless, we establish generalization upper bounds on the counterfactual loss and ITE error of the target task, demonstrating the feasibility of ITE knowledge transfer. Subsequently, we introduce a framework with a new Causal Inference Task Affinity (CITA) measure for ITE knowledge transfer. Specifically, we use CITA to find the closest source task to the target task and utilize it for ITE knowledge transfer. Empirical studies are provided, demonstrating the efficacy of the proposed method. We observe that ITE knowledge transfer can significantly (up to 95%) reduce the amount of data required for ITE estimation.	uXlB3rveiR	Transfer learning for individual treatment effect estimation	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	aloui23a	0	Transfer learning for individual treatment effect estimation	56	66	56-66	56	false	Aloui, Ahmed and Dong, Juncheng and Le, Cat P and Tarokh, Vahid	given family Ahmed Aloui given family Juncheng Dong given family Cat P Le given family Vahid Tarokh	2023-07-02		Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence	216	inproceedings	date-parts 2023 7 2	https://proceedings.mlr.press/v216/aloui23a/aloui23a.pdf	label link Supplementary PDF https://proceedings.mlr.press/v216/aloui23a/aloui23a-supp.pdf