Weakly Supervised Disentangled Generative Causal Representation Learning

TL;DR

This paper introduces DEAR, a novel method for learning disentangled causal representations that accounts for causal relationships among factors, enabling causal controllable generation and improving downstream task robustness.

Contribution

The paper presents DEAR, a new disentangled learning approach using SCM priors within a GAN framework, addressing limitations of previous methods that assume independent factors.

Findings

DEAR successfully disentangles causally related factors.

It enables causal controllable generation.

It improves sample efficiency and robustness in downstream tasks.

Abstract

This paper proposes a Disentangled gEnerative cAusal Representation (DEAR) learning method under appropriate supervised information. Unlike existing disentanglement methods that enforce independence of the latent variables, we consider the general case where the underlying factors of interests can be causally related. We show that previous methods with independent priors fail to disentangle causally related factors even under supervision. Motivated by this finding, we propose a new disentangled learning method called DEAR that enables causal controllable generation and causal representation learning. The key ingredient of this new formulation is to use a structural causal model (SCM) as the prior distribution for a bidirectional generative model. The prior is then trained jointly with a generator and an encoder using a suitable GAN algorithm incorporated with supervised information on the ground-truth factors and their underlying causal structure. We provide theoretical justification on the identifiability and asymptotic convergence of the proposed method. We conduct extensive experiments on both synthesized and real data sets to demonstrate the effectiveness of DEAR in causal controllable generation, and the benefits of the learned representations for downstream tasks in terms of sample efficiency and distributional robustness.