Kolmogorov-Arnold causal generative models
This addresses the need for auditability in high-stakes tabular decision-making domains, though it is incremental as it builds on existing causal generative modeling with a focus on transparency.
The authors tackled the problem of opaque mechanisms in deep causal models by proposing KaCGM, a causal generative model using Kolmogorov-Arnold Networks for interpretability, achieving competitive performance on benchmarks and demonstrating simplified structural equations in a real-world case study.
Causal generative models provide a principled framework for answering observational, interventional, and counterfactual queries from observational data. However, many deep causal models rely on highly expressive architectures with opaque mechanisms, limiting auditability in high-stakes domains. We propose KaCGM, a causal generative model for mixed-type tabular data where each structural equation is parameterized by a Kolmogorov--Arnold Network (KAN). This decomposition enables direct inspection of learned causal mechanisms, including symbolic approximations and visualization of parent--child relationships, while preserving query-agnostic generative semantics. We introduce a validation pipeline based on distributional matching and independence diagnostics of inferred exogenous variables, allowing assessment using observational data alone. Experiments on synthetic and semi-synthetic benchmarks show competitive performance against state-of-the-art methods. A real-world cardiovascular case study further demonstrates the extraction of simplified structural equations and interpretable causal effects. These results suggest that expressive causal generative modeling and functional transparency can be achieved jointly, supporting trustworthy deployment in tabular decision-making settings. Code: https://github.com/aalmodovares/kacgm