CauScale: Neural Causal Discovery at Scale

TL;DR

CauScale introduces a neural causal discovery architecture that efficiently scales to large graphs with up to 1000 nodes, significantly improving speed and maintaining high accuracy in causal inference tasks.

Contribution

The paper presents CauScale, a novel neural architecture that enhances scalability and efficiency in causal discovery for large graphs, overcoming previous computational limitations.

Findings

Achieves 99.6% mAP on in-distribution data

Attains 84.4% mAP on out-of-distribution data

Provides 4-13,000 times faster inference than prior methods

Abstract

Causal discovery is essential for advancing data-driven fields such as scientific AI and data analysis, yet existing approaches face significant time- and space-efficiency bottlenecks when scaling to large graphs. To address this challenge, we present CauScale, a neural architecture designed for efficient causal discovery that scales inference to graphs with up to 1000 nodes. CauScale improves time efficiency via a reduction unit that compresses data embeddings and improves space efficiency by adopting tied attention weights to avoid maintaining axis-specific attention maps. To keep high causal discovery accuracy, CauScale adopts a two-stream design: a data stream extracts relational evidence from high-dimensional observations, while a graph stream integrates statistical graph priors and preserves key structural signals. CauScale successfully scales to 500-node graphs during training, where prior work fails due to space limitations. Across testing data with varying graph scales and causal mechanisms, CauScale achieves 99.6% mAP on in-distribution data and 84.4% on out-of-distribution data, while delivering 4-13,000 times inference speedups over prior methods. Our project page is at https://github.com/OpenCausaLab/CauScale.