DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning

2025-06-11

AI Summary

Autoencoders suffer from training instability due to GAN integration and latent-space redundancy under high compression ratios. Method: This paper proposes the Diffusion-Guided Autoencoder (DGAE), the first framework to embed a conditional diffusion prior into the decoding process—replacing conventional reconstruction with progressive denoising, and jointly optimizing perceptual loss and reconstruction consistency. DGAE integrates a variational autoencoder architecture with a conditional diffusion model, enabling compact latent representations without compromising generation quality. Contribution/Results: DGAE reduces latent dimensionality by 50%, substantially mitigating over-parameterization while maintaining state-of-the-art (SOTA) performance on both image reconstruction and generation tasks on ImageNet-1K. The diffusion module converges approximately 40% faster than baseline approaches, achieving an effective balance among high compression ratio, training stability, and representation compactness.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Autoencoders empower state-of-the-art image and video generative models by compressing pixels into a latent space through visual tokenization. Although recent advances have alleviated the performance degradation of autoencoders under high compression ratios, addressing the training instability caused by GAN remains an open challenge. While improving spatial compression, we also aim to minimize the latent space dimensionality, enabling more efficient and compact representations. To tackle these challenges, we focus on improving the decoder's expressiveness. Concretely, we propose DGAE, which employs a diffusion model to guide the decoder in recovering informative signals that are not fully decoded from the latent representation. With this design, DGAE effectively mitigates the performance degradation under high spatial compression rates. At the same time, DGAE achieves state-of-the-art performance with a 2x smaller latent space. When integrated with Diffusion Models, DGAE demonstrates competitive performance on image generation for ImageNet-1K and shows that this compact latent representation facilitates faster convergence of the diffusion model.

Problem

• Reducing training instability caused by GAN in autoencoders
• Minimizing latent space dimensionality for efficient representation
• Improving decoder expressiveness with diffusion model guidance

Innovation

• Uses diffusion model to guide decoder
• Reduces latent space dimensionality by 2x
• Improves performance under high compression