Semantic Communications and Lossy Compression with Side Information
Keunyoung Kim, Woo Yong Lee, Young‐Jo Ko · 2024
Semantic communications aim to convey precise meanings efficiently rather than transmitting bits accurately. Inspired by lossy compression with side information, we propose a communication scheme that transmits only task-essential data while achieving desired outcomes. Our approach employs machine learning to construct contextual information and compress data into a finite set of latent vectors.