DUET:一种用于高效设备模型泛化的免调优设备-云协同参数生成框架
DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization
AI总结:
针对端侧模型泛化中微调成本高、易过拟合的问题,本文提出免调优的设备-云协同参数生成框架DUET,由云端依据实时设备数据直接生成个性化权重,并在三个公开数据集上验证其有效性与泛化性。
摘要:
设备模型泛化(Device Model Generalization,DMG)是端侧机器学习应用中一个实用但研究不足的课题。其目标是提升预训练模型部署到资源受限设备上时的泛化能力,例如提升预训练云模型在智能手机上的性能。尽管已有大量工作研究云端与设备之间的数据分布偏移,但其中大多数聚焦于在单个设备的个性化数据上对模型进行微调,以促进DMG。尽管这些方法效果可观,但它们需要在设备端重新训练;由于在实时数据上执行梯度计算会带来过拟合问题和较高时间延迟,这在实际中并不可行。本文认为,微调所带来的计算成本在很大程度上是不必要的。因此,我们提出了一种在不增加计算成本的情况下改进DMG的新视角,即设备特定参数生成,它将数据分布直接映射为参数。具体而言,我们提出了一个高效的设备-云协同参数生成框架DUET。DUET部署在功能强大的云服务器上,只需要低成本的前向传播以及设备与云之间较低的数据传输延迟。通过这种方式,DUET能够以单个设备的个性化实时数据为条件,预演设备特定模型权重的实现。重要的是,我们的DUET巧妙地将云端与设备连接为一场“二重奏”式协作,使DMG摆脱微调,并实现更快、更准确的DMG范式。我们在三个公开数据集上对DUET进行了广泛实验研究,实验结果证实了该框架在不同DMG任务上的有效性和泛化能力。
英文摘要:
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 require on-device re-training, which is practically infeasible due to the overfitting problem and high time delay when performing gradient calculation on real-time data. In this paper, we argue that the computational cost brought by fine-tuning can be rather unnecessary. We consequently present a novel perspective to improving DMG without increasing computational cost, i.e., device-specific parameter generation which directly maps data distribution to parameters. Specifically, we propose an efficient Device-cloUd collaborative parametErs generaTion framework DUET. DUET is deployed on a powerful cloud server that only requires the low cost of forwarding propagation and low time delay of data transmission between the device and the cloud. By doing so, DUET can rehearse the device-specific model weight realizations conditioned on the personalized real-time data for an individual device. Importantly, our DUET elegantly connects the cloud and device as a 'duet' collaboration, frees the DMG from fine-tuning, and enables a faster and more accurate DMG paradigm. We conduct an extensive experimental study of DUET on three public datasets, and the experimental results confirm our framework's effectiveness and generalisability for different DMG tasks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。