DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization. (arXiv:2209.05227v2 [cs.DC] UPDATED)

Device Model Generalization (DMG) is a practical yet under-investigated
research topic for on-device machine learning applications. It aims to improve
the generalization ability of pre-trained models when deployed on
resource-constrained devices, such as improving the performance of pre-trained
cloud models on smart mobiles. While quite a lot of works have investigated the
data distribution shift across clouds and devices, most of them focus on model
fine-tuning on personalized data for individual devices to facilitate DMG.
Despite their promising, these approaches …

arxiv cloud collaborative framework free model generalization