Deep Generative Modeling Reshapes Compression and Transmission: From Efficiency to Resiliency

TL;DR

This paper explores how deep generative models can enhance data compression and transmission resiliency by leveraging their predictive capabilities, bridging information theory and machine learning.

Contribution

It introduces a dual-functionality perspective of generative models for both efficient compression and error concealment in communication systems.

Findings

Generative models serve as powerful predictors capturing complex semantic relationships.

They enable improved data compression efficiency.

They facilitate error restoration, enhancing transmission resiliency.

Abstract

Information theory and machine learning are inextricably linked and have even been referred to as "two sides of the same coin". One particularly elegant connection is the essential equivalence between probabilistic generative modeling and data compression or transmission. In this article, we reveal the dual-functionality of deep generative models that reshapes both data compression for efficiency and transmission error concealment for resiliency. We present how the contextual predictive capabilities of powerful generative models can be well positioned to be strong compressors and estimators. In this sense, we advocate for viewing the deep generative modeling problem through the lens of end-to-end communications, and evaluate the compression and error restoration capabilities of foundation generative models. We show that the kernel of many large generative models is powerful predictor that can capture complex relationships among semantic latent variables, and the communication viewpoints provide novel insights into semantic feature tokenization, contextual learning, and usage of deep generative models. In summary, our article highlights the essential connections of generative AI to source and channel coding techniques, and motivates researchers to make further explorations in this emerging topic.