arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.06374cs.NIcs.AIcs.LG
收藏

用于无线边缘学习的知识蒸馏

Knowledge Distillation For Wireless Edge Learning

Purdue University(普渡大学)

Ahmed P. Mohamed, Abu Shafin Mohammad Mahdee Jameel, Aly El Gamal

摘要:

在本文中,我们提出了一个框架,通过最近收集的数据集预测帧错误的合作频谱拥挤的无线环境中的DARPA频谱合作挑战(SC2)。我们采用分布式深度边缘学习,在边缘节点和中央云之间共享。使用这个接近实践的数据集,我们发现广泛使用的联邦学习方法,特别是那些保护隐私的方法,在广泛的设置中比本地训练更差。因此,我们利用合成少数过采样技术,以保持隐私,通过避免本地数据传输到云,并利用知识蒸馏的目的是受益于高云计算和存储能力。所提出的框架实现了比本地和联邦训练方法更好的整体性能,同时对灾难性故障以及导致高帧出错率的具有挑战性的信道条件具有鲁棒性。

英文摘要:

In this paper, we propose a framework for predicting frame errors in the collaborative spectrally congested wireless environments of the DARPA Spectrum Collaboration Challenge (SC2) via a recently collected dataset. We employ distributed deep edge learning that is shared among edge nodes and a central cloud. Using this close-to-practice dataset, we find that widely used federated learning approaches, specially those that are privacy preserving, are worse than local training for a wide range of settings. We hence utilize the synthetic minority oversampling technique to maintain privacy via avoiding the transfer of local data to the cloud, and utilize knowledge distillation with an aim to benefit from high cloud computing and storage capabilities. The proposed framework achieves overall better performance than both local and federated training approaches, while being robust against catastrophic failures as well as challenging channel conditions that result in high frame error rates.

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。

↑