arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.09194cs.CVcs.LGcs.NI
收藏

基于DRL的车联网中抗运动模糊联邦自监督学习资源分配

DRL-Based Resource Allocation for Motion Blur Resistant Federated Self-Supervised Learning in IoV

School of Internet of Things Engineering, Jiangnan University(江南大学物联网工程学院);Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University(清华大学电子工程系,北京信息科技大学国家信息科学与技术研究中心);Qualcomm(高通);State Key Lab. of ISN and School of Telecommunications Engineering, Xidian University(西安电子科技大学信息与通信系统国家重点实验室及电信工程学院);Department of Electronic Engineering, Shanghai Jiao Tong University(上海交通大学电子工程系);Department of Electrical and Computer Engineering, the Hong Kong University of Science and Technology (HKUST)(香港科技大学电子与计算机工程系)

Xueying Gu, Qiong Wu, Pingyi Fan, Qiang Fan, Nan Cheng, Wen Chen, Khaled B. Letaief

AI总结:

针对车联网中联邦自监督学习的隐私与运动模糊问题,提出基于SimCo的抗模糊方法BFSSL,并设计DRL资源分配方案以最小化能耗和延迟,仿真验证其有效性。

摘要:

在车联网(IoV)中,联邦学习(FL)通过聚合本地模型而不共享数据,提供了一种保护隐私的解决方案。传统的监督学习需要带有标签的图像数据,但数据标注涉及大量人工工作。联邦自监督学习(FSSL)利用自监督学习(SSL)在FL中进行本地训练,在保护隐私的同时消除了对标签的需求。与其他SSL方法相比,动量对比(MoCo)通过创建字典来减少对计算资源和存储空间的需求。然而,在FSSL中使用MoCo需要将车辆上的本地字典上传到基站(BS),这存在隐私泄露的风险。简化对比(SimCo)通过使用双温度代替字典来控制样本分布,解决了基于MoCo的FSSL中的隐私泄露问题。此外,考虑到运动模糊对模型聚合的负面影响,并基于SimCo,我们提出了一种抗运动模糊的FSSL方法,称为BFSSL。进一步地,我们通过提出一种基于深度强化学习(DRL)的资源分配方案(称为DRL-BFSSL)来解决BFSSL过程中的能耗和延迟问题。在该方案中,BS分配车辆的中央处理器(CPU)频率和传输功率,以最小化能耗和延迟,同时根据运动模糊程度聚合接收到的模型。仿真结果验证了我们提出的聚合和资源分配方法的有效性。

英文摘要:

In the Internet of Vehicles (IoV), Federated Learning (FL) provides a privacy-preserving solution by aggregating local models without sharing data. Traditional supervised learning requires image data with labels, but data labeling involves significant manual effort. Federated Self-Supervised Learning (FSSL) utilizes Self-Supervised Learning (SSL) for local training in FL, eliminating the need for labels while protecting privacy. Compared to other SSL methods, Momentum Contrast (MoCo) reduces the demand for computing resources and storage space by creating a dictionary. However, using MoCo in FSSL requires uploading the local dictionary from vehicles to Base Station (BS), which poses a risk of privacy leakage. Simplified Contrast (SimCo) addresses the privacy leakage issue in MoCo-based FSSL by using dual temperature instead of a dictionary to control sample distribution. Additionally, considering the negative impact of motion blur on model aggregation, and based on SimCo, we propose a motion blur-resistant FSSL method, referred to as BFSSL. Furthermore, we address energy consumption and delay in the BFSSL process by proposing a Deep Reinforcement Learning (DRL)-based resource allocation scheme, called DRL-BFSSL. In this scheme, BS allocates the Central Processing Unit (CPU) frequency and transmission power of vehicles to minimize energy consumption and latency, while aggregating received models based on the motion blur level. Simulation results validate the effectiveness of our proposed aggregation and resource allocation methods.

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。

↑