Kaddour, J;
ZHU, Y;
Liu, Q;
Kusner, M;
Silva, R;
(2021)
Causal Effect Inference for Structured Treatments.
In: Ranzato, M and Beygelzimer, A and Liang, PS and Vaughan, JW, (eds.)
Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021).
Neural Information Processing Systems (NeurIPS)
(In press).
Preview |
Text
2106.01939.pdf - Published Version Download (4MB) | Preview |
Abstract
We address the estimation of conditional average treatment effects (CATEs) for structured treatments (e.g., graphs, images, texts). Given a weak condition on the effect, we propose the generalized Robinson decomposition, which (i) isolates the causal estimand (reducing regularization bias), (ii) allows one to plug in arbitrary models for learning, and (iii) possesses a quasi-oracle convergence guarantee under mild assumptions. In experiments with small-world and molecular graphs we demonstrate that our approach outperforms prior work in CATE estimation.
Type: | Proceedings paper |
---|---|
Title: | Causal Effect Inference for Structured Treatments |
Event: | NeurIPS 2021: Thirty-fifth Conference on Neural Information Processing Systems |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | https://proceedings.neurips.cc/paper/2021/hash/d02... |
Language: | English |
Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10138512 |
Archive Staff Only
![]() |
View Item |