arXiv 2002.001572020-02-01cs.AIeess.IV

用于协作智能的共享移动云推理

Shared Mobile-Cloud Inference for Collaborative Intelligence

School of Engineering Science（工程科学学院）；Simon Fraser University（西蒙菲莎大学）；Burnaby, BC, V5A 1S6, Canada（加拿大不列颠哥伦比亚省本拿比市）

Mateen Ulhaq, Ivan V. Bajić

备注：: 5 pages, 3 figures

摘要：

随着移动设备的AI应用变得越来越普遍，越来越需要更快的执行速度和更低的神经模型推理能耗。从历史上看，与只能在云上运行的大型最先进的研究模型相比，在移动设备上运行的模型更小，更简单。然而，仅云推理具有缺点，例如增加的网络带宽消耗和更高的延迟。此外，仅云推理要求将输入数据（图像、音频）完全传输到云端，这引发了对潜在隐私泄露的担忧。我们展示了一种替代方法：共享移动云推理。在移动设备上执行部分推理，以便降低输入数据的维数，并得到紧凑的特征张量，该特征张量是输入信号的潜在空间表示。然后将特征张量传输到服务器以进行进一步的推断。该策略可以改善推理延迟、能量消耗和网络带宽使用，以及提供隐私保护，因为原始信号从未离开移动设备。进一步的性能增益可以通过在传输之前压缩特征张量来实现。

英文摘要：

As AI applications for mobile devices become more prevalent, there is an increasing need for faster execution and lower energy consumption for neural model inference. Historically, the models run on mobile devices have been smaller and simpler in comparison to large state-of-the-art research models, which can only run on the cloud. However, cloud-only inference has drawbacks such as increased network bandwidth consumption and higher latency. In addition, cloud-only inference requires the input data (images, audio) to be fully transferred to the cloud, creating concerns about potential privacy breaches. We demonstrate an alternative approach: shared mobile-cloud inference. Partial inference is performed on the mobile in order to reduce the dimensionality of the input data and arrive at a compact feature tensor, which is a latent space representation of the input signal. The feature tensor is then transmitted to the server for further inference. This strategy can improve inference latency, energy consumption, and network bandwidth usage, as well as provide privacy protection, because the original signal never leaves the mobile. Further performance gain can be achieved by compressing the feature tensor before its transmission.

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。

摘要：

英文摘要：

相关论文