Waste Not, Want Not: Service Migration-Assisted Federated Intelligence for Multi-Modality Mobile Edge Computing
Waste Not, Want Not: Service Migration-Assisted Federated Intelligence for Multi-Modality Mobile Edge Computing
复制标题
DOI：
10.1145/3565287.3610277
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Hansong Zhou;Shaoying Wang;Chutian Jiang;Xiaonan Zhang;Linke Guo;Yukun Yuan
中科院分区：
文献类型：
--
作者：
Hansong Zhou;Shaoying Wang;Chutian Jiang;Xiaonan Zhang;Linke Guo;Yukun Yuan
未来的移动的边缘计算（MEC）被设想为使用多模态数据为延迟敏感的学习任务提供联合智能。传统的水平联邦学习（FL）在处理复杂的多模态模型时存在资源需求高的问题。多模态外语（MFL），另一方面，提供了一个更有效的方法来学习多模态数据。在MFL中，整个多模态模型被分成几个子模型，每个子模型都针对特定的数据模态进行定制，并在指定的边缘上进行训练。由于子模型比多模态模型小得多，因此MFL需要更少的计算资源并减少通信时间。然而，在MEC上部署MFL面临着设备移动性和边缘异构性的挑战，如果不解决这些问题，可能会对MFL性能产生负面影响。在本文中，我们研究了一个服务迁移辅助的移动的多模态联邦学习（SM3FL）框架，在边缘之间的子模型的服务迁移是启用的。为了有效地利用SM3FL中的通信和计算资源而不浪费，我们开发了服务迁移和数据样本收集的最佳策略，以最大限度地减少挂钟时间，定义为达到学习目标所需的训练时间。我们的实验结果表明，建议SM3FL框架表现出显着的性能，超过其他国家的最先进的FL框架，通过大幅减少计算需求的17.5%，并显着减少挂钟时间的25.3%。
Future mobile edge computing (MEC) is envisioned to provide federated intelligence to delay-sensitive learning tasks with multimodal data. Conventional horizontal federated learning (FL) suffers from high resource demand in response to complicated multi-modal models. Multi-modal FL (MFL), on the other hand, offers a more efficient approach for learning from multi-modal data. In MFL, the entire multi-modal model is split into several sub-models with each tailored to a specific data modality and trained on a designated edge. As sub-models are considerably smaller than the multi-modal model, MFL requires fewer computation resources and reduces communication time. Nevertheless, deploying MFL over MEC faces the challenges of device mobility and edge heterogeneity, which, if not addressed, could negatively impact MFL performance. In this paper, we investigate an Service Migration-assisted Mobile Multi-modal Federated Learning (SM3FL) framework, where the service migration for sub-models between edges is enabled. To effectively utilize both communication and computation resources without extravagance in SM3FL, we develop the optimal strategies of service migration and data sample collection to minimize the wall-clock time, defined as the required training time to reach the learning target. Our experiment results show that the proposed SM3FL framework demonstrates remarkable performance, surpassing other state-of-art FL frameworks via substantially reducing the computing demand by 17.5% and dramatically decreasing the wall-clock time by 25.3%.