Generative Feature Imputing -- A Technique for Error-resilient Semantic Communication

TL;DR

This paper introduces a generative feature imputing framework for semantic communication in 6G networks, enhancing robustness against transmission errors using diffusion models and semantic-aware power allocation.

Contribution

It proposes a novel framework combining spatial error concentration, generative feature imputation with diffusion models, and semantic-aware power allocation for error-resilient SemCom.

Findings

Outperforms DJSCC and JPEG2000 in semantic accuracy.

Achieves lower LPIPS scores under block fading conditions.

Demonstrates robustness to transmission errors in semantic communication.

Abstract

Semantic communication (SemCom) has emerged as a promising paradigm for achieving unprecedented communication efficiency in sixth-generation (6G) networks by leveraging artificial intelligence (AI) to extract and transmit the underlying meanings of source data. However, deploying SemCom over digital systems presents new challenges, particularly in ensuring robustness against transmission errors that may distort semantically critical content. To address this issue, this paper proposes a novel framework, termed generative feature imputing, which comprises three key techniques. First, we introduce a spatial error concentration packetization strategy that spatially concentrates feature distortions by encoding feature elements based on their channel mappings, a property crucial for both the effectiveness and reduced complexity of the subsequent techniques. Second, building on this strategy, we propose a generative feature imputing method that utilizes a diffusion model to efficiently reconstruct missing features caused by packet losses. Finally, we develop a semantic-aware power allocation scheme that enables unequal error protection by allocating transmission power according to the semantic importance of each packet. Experimental results demonstrate that the proposed framework outperforms conventional approaches, such as Deep Joint Source-Channel Coding (DJSCC) and JPEG2000, under block fading conditions, achieving higher semantic accuracy and lower Learned Perceptual Image Patch Similarity (LPIPS) scores.