2020/06/14 by Frederik Träuble, Träuble, Frederik, Elliot Creager +13 · 3 citations
Computer Science · #Computability, Logic, AI Algorithms #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Neural Networks and Applications
paper · pdf · doi:10.48550/arxiv.2006.07886
openalex publication_date 2020/06/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data in a large-scale empirical study (including 4260 models). We show and quantify that systematically induced correlations in the dataset are being learned and reflected in the latent representations, which has implications for downstream applications of disentanglement such as fairness. We also demonstrate how to resolve these latent correlations, either using weak supervision during training or by post-hoc correcting a pre-trained model with a small number of labels.