Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery

About

Real-world data often violates the equal-variance assumption (homoscedasticity), making it essential to account for heteroscedastic noise in causal discovery. In this work, we explore heteroscedastic symmetric noise models (HSNMs), where the effect $Y$ is modeled as $Y = f(X) + \sigma(X)N$, with $X$ as the cause and $N$ as independent noise following a symmetric distribution. We introduce a novel criterion for identifying HSNMs based on the skewness of the score (i.e., the gradient of the log density) of the data distribution. This criterion establishes a computationally tractable measurement that is zero in the causal direction but nonzero in the anticausal direction, enabling the causal direction discovery. We extend this skewness-based criterion to the multivariate setting and propose SkewScore, an algorithm that handles heteroscedastic noise without requiring the extraction of exogenous noise. We also conduct a case study on the robustness of SkewScore in a bivariate model with a latent confounder, providing theoretical insights into its performance. Empirical studies further validate the effectiveness of the proposed method.

Yingyu Lin, Yuxing Huang, Wenqin Liu, Haoran Deng, Ignavier Ng, Kun Zhang, Mingming Gong, Yi-An Ma, Biwei Huang• 2024

Related benchmarks

TaskDatasetResultRank
Causal OrderingSachs
ODR71
12
Runtime EfficiencySynthetic Graphs d=20
Runtime (seconds)2.548
12
Runtime EfficiencySynthetic Graphs d=100
Runtime (s)20.043
12
Runtime EfficiencySynthetic Graphs d=50
Runtime (seconds)8.022
12
Causal OrderingSyntren
ODR49
12
Runtime EfficiencySynthetic Graphs d=10
Runtime (seconds)1.202
12
Runtime EfficiencySynthetic Graphs d=5
Runtime (s)0.543
12
Showing 7 of 7 rows

Other info

Follow for update