A joint optimization scheme integrating memory, computing and offloading for energy-efficient DNN inference and achieves near-optimal performance, and reduces the energy consumption of devices by up to 16.1% compared with benchmarks without memory frequency optimization.
Yun-Chu Han, Zhao-Jun Nan, Sheng Zhou et al.· IEEE Transactions on Mobile...· 0 citations
FedPGT, a progressive gradient transmission scheme for VFL over time-varying channels, where vehicles progressively transmit high-magnitude gradient entries in response to instantaneous channel conditions is proposed, establishing a convergence bound that characterizes the impact of transmitted gradient entries and rev...
Jin-Tao Yan, Tan Chen, Yuxuan Sun et al.· arXiv.org· 0 citations
Sylvas is presented, a synergistic learning value based device scheduling framework for FCL at the wireless edge that supports timely model adaptation under spatio-temporal distribution dynamics and effectively exploits unlabeled data.
Yuxuan Sun, Yuxuan Bai, Tan Chen et al.· 0 citations
The impact of memory frequency and computing frequency on DNN inference time is considered, and a low-complexity heuristic algorithm is proposed to effectively solve the overall problem with polynomial time complexity.