DeepAI AI Chat
Log In Sign Up

Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style

by   Julius von Kügelgen, et al.

Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant. We seek to understand the empirical success of this approach from a theoretical perspective. We formulate the augmentation process as a latent variable model by postulating a partition of the latent representation into a content component, which is assumed invariant to augmentation, and a style component, which is allowed to change. Unlike prior work on disentanglement and independent component analysis, we allow for both nontrivial statistical and causal dependencies in the latent space. We study the identifiability of the latent representation based on pairs of views of the observations and prove sufficient conditions that allow us to identify the invariant content partition up to an invertible mapping in both generative and discriminative settings. We find numerical simulations with dependent latent variables are consistent with our theory. Lastly, we introduce Causal3DIdent, a dataset of high-dimensional, visually complex images with rich causal dependencies, which we use to study the effect of data augmentations performed in practice.


page 8

page 22

page 23

page 24

page 28


Learning Dependencies of Discrete Speech Representations with Neural Hidden Markov Models

While discrete latent variable models have had great success in self-sup...

ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints

Learning self-supervised video representation predominantly focuses on d...

Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning

In contrastive self-supervised learning, the common way to learn discrim...

SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning

Self-supervised learning has been shown to be very effective in learning...

Unpaired Multi-Domain Causal Representation Learning

The goal of causal representation learning is to find a representation o...

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation

Good data augmentation is one of the key factors that lead to the empiri...

Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective

Learning behavioral patterns from observational data has been a de-facto...