Our paper has been accepted to the Workshop on Ubiquitous Network Intelligence for Next Generation Wireless Networks in IEEE GLOBECOM 2024). This work is collaborative research with Prof. Nishio at Tokyo Institute of Technology. This paper proposes neural architectures with vector quantized bottlenecks for split inference to reduce the traffic between edge devices and servers.
- Chen Yen-Hsiu, Yoichi Hirose, Shoma Shimizu, Shota Saito, Kento Uchida, Shinichi Shirakawa, and Takayuki Nishio: Enhancing Latency-Accuracy Tradeoff in Dynamic Split Inference via Vector Quantized Bottleneck, 2024 IEEE Globecom Workshops, Ubiquitous Network Intelligence for Next Generation Wireless Networks, Cape Town, South Africa, December 8-12, 2024.