SurvCaus : Representation Balancing for Survival Causal Inference

TL;DR

This paper introduces SurvCaus, a neural network framework that applies representation balancing to estimate individual treatment effects in survival analysis, providing theoretical guarantees and outperforming baseline methods on synthetic data.

Contribution

It presents a novel neural network approach with theoretical guarantees for causal inference in survival settings, handling censored data effectively.

Findings

Outperforms baseline methods on synthetic datasets

Provides theoretical guarantees for survival causal inference

Accurately predicts individual survival functions and CATEs

Abstract

Individual Treatment Effects (ITE) estimation methods have risen in popularity in the last years. Most of the time, individual effects are better presented as Conditional Average Treatment Effects (CATE). Recently, representation balancing techniques have gained considerable momentum in causal inference from observational data, still limited to continuous (and binary) outcomes. However, in numerous pathologies, the outcome of interest is a (possibly censored) survival time. Our paper proposes theoretical guarantees for a representation balancing framework applied to counterfactual inference in a survival setting using a neural network capable of predicting the factual and counterfactual survival functions (and then the CATE), in the presence of censorship, at the individual level. We also present extensive experiments on synthetic and semisynthetic datasets that show that the proposed extensions outperform baseline methods.