Pseudo-Nonlinear Data Augmentation: A Constrained Energy Minimization Viewpoint

TL;DR

This paper introduces a novel energy-based data augmentation method that constructs a geometrically aware latent space, enabling efficient, controllable augmentation across various data modalities, and demonstrates competitive performance in downstream tasks.

Contribution

It presents a new data augmentation framework based on energy modeling and information geometry, differing from traditional generative model approaches.

Findings

Achieves competitive results in downstream tasks.

Provides fine-grained controllability in data augmentation.

Supports efficient encoding and decoding procedures.

Abstract

We propose a simple yet novel data augmentation method for general data modalities based on energy-based modeling and principles from information geometry. Unlike most existing learning-based data augmentation methods, which rely on learning latent representations with generative models, our proposed framework enables an intuitive construction of a geometrically aware latent space that represents the structure of the data itself, supporting efficient and explicit encoding and decoding procedures. We then present and discuss how to design latent spaces that will subsequently control the augmentation with the proposed algorithm. Empirical results demonstrate that our data augmentation method achieves competitive performance in downstream tasks compared to other baselines, while offering fine-grained controllability that is lacking in the existing literature.