arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.04249cs.LGcs.AIcs.DC
收藏

面向协作推理系统的联邦学习:以早退网络为例

Federated Learning for Collaborative Inference Systems: The Case of Early Exit Networks

SAP Labs France(SAP法国实验室);Inria(法国国家信息与自动化研究所);Huawei(华为)

Caelin Kaplan, Angelo Rodio, Tareq Si Salem, Chuan Xu, Giovanni Neglia

AI总结:

针对协作推理系统中服务速率异质性问题,提出一种新型联邦学习方法,具备理论保证并在非均匀场景下超越现有最先进算法。

摘要:

随着物联网(IoT)技术的进步,传感器和智能手机等终端设备逐渐配备了根据其本地内存和计算约束定制的AI模型。本地推理降低了通信成本和延迟;然而,这些较小的模型通常比部署在边缘服务器或云端的更复杂的模型性能逊色。协作推理系统(CIS)通过使较小的设备能够将其部分推理任务卸载给能力更强的设备来解决这种性能权衡。这些系统通常部署共享大量参数的分层模型,例如利用早退(early exits)或有序丢弃(ordered dropout)策略的深度神经网络(DNN)。在这种情况下,可以采用联邦学习(FL)来联合训练CIS内的模型。然而,传统的训练方法忽略了CIS在推理过程中的运行动态,特别是客户端之间服务速率可能存在的严重异质性。为了解决这一空白,我们提出了一种专门用于CIS的新型联邦学习方法,该方法考虑了这些服务速率的变化。我们的框架不仅提供了严格的理论保证,而且在推理请求速率或数据可用性在客户端之间不均匀的场景中,超越了最先进的(SOTA)CIS训练算法。

英文摘要:

As Internet of Things (IoT) technology advances, end devices like sensors and smartphones are progressively equipped with AI models tailored to their local memory and computational constraints. Local inference reduces communication costs and latency; however, these smaller models typically underperform compared to more sophisticated models deployed on edge servers or in the cloud. Cooperative Inference Systems (CISs) address this performance trade-off by enabling smaller devices to offload part of their inference tasks to more capable devices. These systems often deploy hierarchical models that share numerous parameters, exemplified by Deep Neural Networks (DNNs) that utilize strategies like early exits or ordered dropout. In such instances, Federated Learning (FL) may be employed to jointly train the models within a CIS. Yet, traditional training methods have overlooked the operational dynamics of CISs during inference, particularly the potential high heterogeneity in serving rates across clients. To address this gap, we propose a novel FL approach designed explicitly for use in CISs that accounts for these variations in serving rates. Our framework not only offers rigorous theoretical guarantees, but also surpasses state-of-the-art (SOTA) training algorithms for CISs, especially in scenarios where inference request rates or data availability are uneven among clients.

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。

↑