Semantic communication improves storage use with reusable knowledge bases
Storage-Scalable Progressive Semantic Communication via Knowledge-Base Reuse
Machine LearningNetworking and Internet Architecture
Summary
Sending information in a way that focuses on meaning, called semantic communication, can use special sets of knowledge called knowledge bases (KBs). Usually, systems either use one KB but with limited detail or multiple KBs which use a lot of storage. The authors propose a method that reuses a small set of KBs across several stages of refining communication, so storage needs don’t grow as more stages are added. They also add a technique to guide these stages to improve the quality of the information step by step. Their tests show this approach keeps good performance while using less storage space.
What this means in practice
- •For network engineers: Implement communication systems that adjust transmitted data progressively while minimizing memory use for knowledge bases in devices.
- •For data storage teams: Manage knowledge base resources efficiently to support scalable progressive encoding schemes without large storage cost increases.
Authors
Heng Zhu, Ye Liu, Kun Zhu, Feifei Song
Abstract
Existing knowledge-base-assisted semantic communication schemes commonly adopt either single knowledge-base quantization (SKBQ) or multi-knowledge-base residual quantization (MKBQ). SKBQ incurs limited storage overhead but has restricted quantization capacity, whereas MKBQ supports progressive refinement by assigning an independent knowledge base (KB) to each stage, causing the KB storage to grow linearly with the transmission depth. To address this problem, we propose storage-scalable knowledge-base reuse quantization (SSKBQ), which reuses a compact set of KBs across multiple residual refinement stages and thereby decouples the number of transmission stages from the number of maintained KBs. A stage-aware residual supervision mechanism is further introduced to regularize intermediate quantized representations and encourage progressive refinement. Experimental results demonstrate that KB reuse provides an effective solution to the storage scalability problem while maintaining competitive progressive reconstruction performance.