Attention-aware Semantic Communications for Collaborative Inference

arXiv:2404.07217v1 Announce Type: cross
Abstract: We propose a communication-efficient collaborative inference framework in the domain of edge inference, focusing on the efficient use of vision transformer (ViTs) models. The partitioning strategy of conventional collaborative inference fails to reduce communication cost because of the inherent architecture of ViTs maintaining consistent layer dimensions across the entire transformer encoder. Therefore, instead of employing the partitioning strategy, our framework utilizes a lightweight ViT model on the edge device, with the server deploying a complicated …

abstract architecture arxiv attention collaborative communication communications consistent cost cs.ai cs.cv cs.lg dimensions domain edge eess.sp framework inference layer partitioning reduce semantic strategy transformer type vision