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

2025-08-25

AI Summary

To address semantic distortion and insufficient robustness caused by transmission errors in 6G semantic communications, this paper proposes a generative feature imputation framework. The framework innovatively integrates three key techniques: (1) a spatial error concentration packaging strategy to enhance local controllability of channel bit errors; (2) a diffusion-model-based, AI-driven feature recovery mechanism for high-fidelity semantic reconstruction; and (3) semantic-importance-aware unequal error protection with power allocation to improve resource efficiency. Experimental evaluations under block-fading channels demonstrate that the proposed method significantly outperforms DJSCC and JPEG2000, achieving a +12.7% gain in semantic accuracy and a −38.4% reduction in LPIPS distortion. To the best of our knowledge, this is the first work to jointly optimize end-to-end semantic robustness and efficient recovery at the semantic level.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• Ensures robustness against transmission errors in semantic communication
• Reconstructs missing features caused by packet losses using diffusion models
• Allocates transmission power based on semantic importance of packets

Innovation

• Spatial error concentration packetization strategy
• Generative feature imputing using diffusion model
• Semantic-aware unequal error power allocation