Less Greedy Equivalence Search

TL;DR

Less Greedy Equivalence Search (LGES) improves causal discovery by being faster, more accurate, and robust, while maintaining theoretical guarantees, and can incorporate prior knowledge and interventional data.

Contribution

LGES introduces a targeted modification to GES that enhances speed, accuracy, and robustness, with the ability to use and correct prior knowledge, and incorporate interventional data.

Findings

LGES achieves up to 10-fold speed-up over GES.

LGES reduces structural error significantly compared to GES.

LGES recovers the true equivalence class even with misspecified knowledge.

Abstract

Greedy Equivalence Search (GES) is a classic score-based algorithm for causal discovery from observational data. In the sample limit, it recovers the Markov equivalence class of graphs that describe the data. Still, it faces two challenges in practice: computational cost and finite-sample accuracy. In this paper, we develop Less Greedy Equivalence Search (LGES), a variant of GES that retains its theoretical guarantees while partially addressing these limitations. LGES modifies the greedy step; rather than always applying the highest-scoring insertion, it avoids edge insertions between variables for which the score implies some conditional independence. This more targeted search yields up to a \(10\)-fold speed-up and a substantial reduction in structural error relative to GES. Moreover, LGES can guide the search using prior knowledge, and can correct this knowledge when contradicted by data. Finally, LGES can use interventional data to refine the learned observational equivalence class. We prove that LGES recovers the true equivalence class in the sample limit, even with misspecified knowledge. Experiments demonstrate that LGES outperforms GES and other baselines in speed, accuracy, and robustness to misspecified knowledge. Our code is available at https://github.com/CausalAILab/lges.