arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.04516cs.CV
收藏

边缘深度神经网络的更新压缩

Update Compression for Deep Neural Networks on the Edge

The University of Adelaide(阿德莱德大学);University of New South Wales(新南威尔士大学)

Bo Chen, Ali Bakhshi, Gustavo Batista, Brian Ng, Tat-Jun Chin

摘要:

越来越多的人工智能(AI)应用涉及在边缘设备上执行深度神经网络(DNN)。许多实际原因促使需要在部署后更新边缘设备上的DNN模型,例如改进模型,概念漂移或学习任务的彻底更改。在本文中,我们考虑了这样一种场景,即可以基于DNN模型的副本在服务器端进行再训练,只需要将必要的数据传输到边缘来更新部署的模型。然而,由于带宽限制,我们希望最大限度地减少实现更新所需的传输。我们开发了一种基于矩阵分解的简单方法来压缩模型更新-这与压缩模型本身不同。其关键思想是保留当前模型中的现有知识,并仅优化用于更新的小的附加参数,这些参数可用于在边缘上重建模型。我们将我们的方法与联邦学习中使用的类似技术进行了比较;我们的方法通常需要不到现有方法一半的更新大小才能达到相同的精度。

英文摘要:

An increasing number of artificial intelligence (AI) applications involve the execution of deep neural networks (DNNs) on edge devices. Many practical reasons motivate the need to update the DNN model on the edge device post-deployment, such as refining the model, concept drift, or outright change in the learning task. In this paper, we consider the scenario where retraining can be done on the server side based on a copy of the DNN model, with only the necessary data transmitted to the edge to update the deployed model. However, due to bandwidth constraints, we want to minimise the transmission required to achieve the update. We develop a simple approach based on matrix factorisation to compress the model update -- this differs from compressing the model itself. The key idea is to preserve existing knowledge in the current model and optimise only small additional parameters for the update which can be used to reconstitute the model on the edge. We compared our method to similar techniques used in federated learning; our method usually requires less than half of the update size of existing methods to achieve the same accuracy.

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。

↑