Differentiable Constraint-Based Causal Discovery
This work addresses a fundamental challenge in AI for decision-making and predictions by offering a novel hybrid approach that improves causal discovery in small sample settings, though it is incremental in combining existing paradigms.
The paper tackles the problem of causal discovery from observational data by introducing differentiable d-separation scores through soft logic, enabling gradient-based optimization of conditional independence constraints. The result is robust performance in low-sample regimes, surpassing traditional constraint-based and score-based baselines on a real-world dataset.
Causal discovery from observational data is a fundamental task in artificial intelligence, with far-reaching implications for decision-making, predictions, and interventions. Despite significant advances, existing methods can be broadly categorized as constraint-based or score-based approaches. Constraint-based methods offer rigorous causal discovery but are often hindered by small sample sizes, while score-based methods provide flexible optimization but typically forgo explicit conditional independence testing. This work explores a third avenue: developing differentiable $d$-separation scores, obtained through a percolation theory using soft logic. This enables the implementation of a new type of causal discovery method: gradient-based optimization of conditional independence constraints. Empirical evaluations demonstrate the robust performance of our approach in low-sample regimes, surpassing traditional constraint-based and score-based baselines on a real-world dataset. Code and data of the proposed method are publicly available at https://github$.$com/PurdueMINDS/DAGPA.