On Disentangled Representations Learned from Correlated Data

Francesco Locatello, Bernhard Schölkopf, Anirudh Goyal, Niki Kilbertus, Stefan Bauer, Frederik Träuble, Elliot Creager, Andrea Dittadi

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• ftraeuble/disentanglement_lib — marked official in Papers with Code; named in the paper
• facebookresearch/disentangling-correlated-factors

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.07886")
get_code_for_paper("2006.07886")
have("2006.07886")

Connect an agent — have() is free.