arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.01049cs.LGcs.DC
收藏

联邦和多任务学习中的能量和通信效率权衡

On the Energy and Communication Efficiency Tradeoffs in Federated and Multi-Task Learning

Consiglio Nazionale delle Ricerche(意大利国家研究委员会);University of Oulu(奥卢大学);Centre for Wireless Communications(无线通信中心)

Stefano Savazzi, Vittorio Rampa, Sanaz Kianoush, Mehdi Bennis

摘要:

联邦学习(FL)的最新进展为设计新颖的策略铺平了道路,该策略通过利用联网设备之间的协作来同时解决多个学习任务。与传统的迁移学习方法相比,多任务学习(MTL)利用任务之间的相关共性来提高效率。通过联合学习多个任务,可以显著减少能量足迹。本文提供了第一次看MTL过程的能源成本驱动的模型不可知元学习(MAML)范式和分布式无线网络中实现的。本文的目标是一个集群的多任务网络设置,自主智能体学习不同的,但相关的任务。MTL过程分两个阶段进行:可以快速适应学习新任务的元模型的优化,以及特定于任务的模型适应阶段,其中学习到的元模型被转移到代理并为特定任务定制。本文分析了机器人环境下多任务强化学习(RL)系统中影响MTL能量平衡的主要因素。结果表明,MAML方法可以减少至少2倍的能源法案相比,传统的方法没有感应传输。此外,它表明,在无线网络中的最佳能量平衡取决于上行链路/下行链路和侧链路通信效率。

英文摘要:

Recent advances in Federated Learning (FL) have paved the way towards the design of novel strategies for solving multiple learning tasks simultaneously, by leveraging cooperation among networked devices. Multi-Task Learning (MTL) exploits relevant commonalities across tasks to improve efficiency compared with traditional transfer learning approaches. By learning multiple tasks jointly, significant reduction in terms of energy footprints can be obtained. This article provides a first look into the energy costs of MTL processes driven by the Model-Agnostic Meta-Learning (MAML) paradigm and implemented in distributed wireless networks. The paper targets a clustered multi-task network setup where autonomous agents learn different but related tasks. The MTL process is carried out in two stages: the optimization of a meta-model that can be quickly adapted to learn new tasks, and a task-specific model adaptation stage where the learned meta-model is transferred to agents and tailored for a specific task. This work analyzes the main factors that influence the MTL energy balance by considering a multi-task Reinforcement Learning (RL) setup in a robotized environment. Results show that the MAML method can reduce the energy bill by at least 2 times compared with traditional approaches without inductive transfer. Moreover, it is shown that the optimal energy balance in wireless networks depends on uplink/downlink and sidelink communication efficiencies.

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。

↑