Self-Guided Generation of Minority Samples Using Diffusion Models

TL;DR

This paper introduces a self-guided diffusion model-based method for generating minority data samples in low-density regions, improving minority sample creation without external classifiers or costly components.

Contribution

The proposed approach uniquely uses a pretrained diffusion model with self-contained likelihood estimation for minority sample generation, eliminating the need for external classifiers.

Findings

Significantly improves minority sample generation quality.

Operates without external classifiers or additional costly components.

Effective on benchmark real datasets.

Abstract

We present a novel approach for generating minority samples that live on low-density regions of a data manifold. Our framework is built upon diffusion models, leveraging the principle of guided sampling that incorporates an arbitrary energy-based guidance during inference time. The key defining feature of our sampler lies in its \emph{self-contained} nature, \ie, implementable solely with a pretrained model. This distinguishes our sampler from existing techniques that require expensive additional components (like external classifiers) for minority generation. Specifically, we first estimate the likelihood of features within an intermediate latent sample by evaluating a reconstruction loss w.r.t. its posterior mean. The generation then proceeds with the minimization of the estimated likelihood, thereby encouraging the emergence of minority features in the latent samples of subsequent timesteps. To further improve the performance of our sampler, we provide several time-scheduling techniques that properly manage the influence of guidance over inference steps. Experiments on benchmark real datasets demonstrate that our approach can greatly improve the capability of creating realistic low-likelihood minority instances over the existing techniques without the reliance on costly additional elements. Code is available at \url{https://github.com/soobin-um/sg-minority}.