分类: 计算机科学 >> 计算机科学的集成理论 提交时间: 2024-03-16
摘要: A novel federated learning training framework for heterogeneous environments is presented, taking into account the diverse network speeds of clients in realistic settings. This framework integrates asynchronous learning algorithms and pruning techniques, effectively addressing the inefficiencies of traditional federated learning algorithms in scenarios involving heterogeneous devices, as well as tackling the staleness issue and inadequate training of certain clients in asynchronous algorithms. Through the incremental restoration of model size during training, the framework expedites model training while preserving model accuracy. Furthermore, enhancements to the federated learning aggregation process are introduced, incorporating a buffering mechanism to enable asynchronous federated learning to operate akin to synchronous learning. Additionally, optimizations in the process of the server transmitting the global model to clients reduce communication overhead. Our experiments across various datasets demonstrate that: (i) significant reductions in training time and improvements in convergence accuracy are achieved compared to conventional asynchronous FL and HeteroFL; (ii) the advantages of our approach are more pronounced in scenarios with heterogeneous clients and non-IID client data.
分类: 电子与通信技术 >> 光电子学与激光技术 分类: 电子与通信技术 >> 半导体技术 提交时间: 2019-08-13
摘要: High focusing-reflection, non-periodic high-contrast grating integrated with a uni-traveling-carrier photodetector (FR-UTC-PD) is proposed to overcome the bandwidth-responsivity trade-off. The responsivity of the FR-UTC-PD is increased by 36.5% while achieving a 3-dB bandwidth of 18 GHz.