CausalKANs: interpretable treatment effect estimation with Kolmogorov-Arnold networks
This addresses the need for trustworthy and auditable individualized decision-making in high-stakes settings like medicine and economics, though it is incremental as it builds on existing causal neural architectures.
The paper tackles the problem of interpretable treatment effect estimation in sensitive domains by proposing causalKANs, a framework that transforms neural estimators into Kolmogorov-Arnold Networks to yield interpretable closed-form formulas while maintaining predictive accuracy, with experiments showing performance on par with neural baselines in CATE error metrics.
Deep neural networks achieve state-of-the-art performance in estimating heterogeneous treatment effects, but their opacity limits trust and adoption in sensitive domains such as medicine, economics, and public policy. Building on well-established and high-performing causal neural architectures, we propose causalKANs, a framework that transforms neural estimators of conditional average treatment effects (CATEs) into Kolmogorov--Arnold Networks (KANs). By incorporating pruning and symbolic simplification, causalKANs yields interpretable closed-form formulas while preserving predictive accuracy. Experiments on benchmark datasets demonstrate that causalKANs perform on par with neural baselines in CATE error metrics, and that even simple KAN variants achieve competitive performance, offering a favorable accuracy--interpretability trade-off. By combining reliability with analytic accessibility, causalKANs provide auditable estimators supported by closed-form expressions and interpretable plots, enabling trustworthy individualized decision-making in high-stakes settings. We release the code for reproducibility at https://github.com/aalmodovares/causalkans .