个性化联邦学习侧重于为各客户端提供个性化模型,旨在提高对异构数据的处理性能,然而现有的个性化联邦学习算法大多以增加客户端参数量为代价提高个性化模型的性能,使计算变得复杂.为了解决此问题,文中提出基于稀疏正则双层优化的个性...个性化联邦学习侧重于为各客户端提供个性化模型,旨在提高对异构数据的处理性能,然而现有的个性化联邦学习算法大多以增加客户端参数量为代价提高个性化模型的性能,使计算变得复杂.为了解决此问题,文中提出基于稀疏正则双层优化的个性化联邦学习算法(Personalized Federated Learning Based on Sparsity Regularized Bi-level Optimization,pFedSRB),在客户端的个性化更新中引入l 1范数稀疏正则化,提升个性化模型的稀疏度,避免不必要的客户端参数更新,降低模型复杂度.将个性化联邦学习建模为双层优化问题,内层优化采用交替方向乘子法,可提高学习速度.在4个联邦学习基准数据集上的实验表明,pFedSRB在异构数据上表现出色,在提高模型性能的同时有效降低训练用时和空间成本.展开更多
While recommendation plays an increasingly critical role in our living, study, work, and entertainment, the recommendations we receive are often for irrelevant, duplicate, or uninteresting products and ser- vices. A c...While recommendation plays an increasingly critical role in our living, study, work, and entertainment, the recommendations we receive are often for irrelevant, duplicate, or uninteresting products and ser- vices. A critical reason for such bad recommendations lies in the intrinsic assumption that recommend- ed users and items are independent and identically distributed （liD） in existing theories and systems. Another phenomenon is that, while tremendous efforts have been made to model specific aspects of users or items, the overall user and item characteristics and their non-IIDness have been overlooked. In this paper, the non-liD nature and characteristics of recommendation are discussed, followed by the non-liD theoretical framework in order to build a deep and comprehensive understanding of the in- trinsic nature of recommendation problems, from the perspective of both couplings and heterogeneity. This non-liD recommendation research triggers the paradigm shift from lid to non-liD recommendation research and can hopefully deliver informed, relevant, personalized, and actionable recommendations. It creates exciting new directions and fundamental solutions to address various complexities including cold-start, sparse data-based, cross-domain, group-based, and shilling attack-related issues.展开更多
This paper presents several useful mixture representations for the reliability function of the residual live of a coherent system with independent but non-identically distributed components. These presentations are ba...This paper presents several useful mixture representations for the reliability function of the residual live of a coherent system with independent but non-identically distributed components. These presentations are based on order statistics, signatures and mean reliability functions. We then discuss some stochastic comparisons of residual lives between two systems based on the stochastic ordering of coefficient vectors （or components） of the two systems. These results form nice extensions of some known results for the case of independent and identically distributed components.展开更多
This letter analyzes the outage probability of opportunistic amplify-and-forward relaying over asymmetric and independent but non-identically distributed (i.n.d) fading environments. The work investigates the scenario...This letter analyzes the outage probability of opportunistic amplify-and-forward relaying over asymmetric and independent but non-identically distributed (i.n.d) fading environments. The work investigates the scenarios where cooperative nodes are located at different geographical locations. As a result, the different signals are affected by different i.n.d fading channels, one may undergo Rician fading distribution and others may undergo Rayleigh fading distribution. In this letter, a lower bound of the outage probability for various asymmetric fading environments is derived at high SNR by applying the initial value theorem. The analytical model is validated through Monte-Carlo simulation results.展开更多
文摘个性化联邦学习侧重于为各客户端提供个性化模型,旨在提高对异构数据的处理性能,然而现有的个性化联邦学习算法大多以增加客户端参数量为代价提高个性化模型的性能,使计算变得复杂.为了解决此问题,文中提出基于稀疏正则双层优化的个性化联邦学习算法(Personalized Federated Learning Based on Sparsity Regularized Bi-level Optimization,pFedSRB),在客户端的个性化更新中引入l 1范数稀疏正则化,提升个性化模型的稀疏度,避免不必要的客户端参数更新,降低模型复杂度.将个性化联邦学习建模为双层优化问题,内层优化采用交替方向乘子法,可提高学习速度.在4个联邦学习基准数据集上的实验表明,pFedSRB在异构数据上表现出色,在提高模型性能的同时有效降低训练用时和空间成本.
文摘While recommendation plays an increasingly critical role in our living, study, work, and entertainment, the recommendations we receive are often for irrelevant, duplicate, or uninteresting products and ser- vices. A critical reason for such bad recommendations lies in the intrinsic assumption that recommend- ed users and items are independent and identically distributed （liD） in existing theories and systems. Another phenomenon is that, while tremendous efforts have been made to model specific aspects of users or items, the overall user and item characteristics and their non-IIDness have been overlooked. In this paper, the non-liD nature and characteristics of recommendation are discussed, followed by the non-liD theoretical framework in order to build a deep and comprehensive understanding of the in- trinsic nature of recommendation problems, from the perspective of both couplings and heterogeneity. This non-liD recommendation research triggers the paradigm shift from lid to non-liD recommendation research and can hopefully deliver informed, relevant, personalized, and actionable recommendations. It creates exciting new directions and fundamental solutions to address various complexities including cold-start, sparse data-based, cross-domain, group-based, and shilling attack-related issues.
基金supported by the National Natural Science Foundation of China(1116102871361020)
文摘This paper presents several useful mixture representations for the reliability function of the residual live of a coherent system with independent but non-identically distributed components. These presentations are based on order statistics, signatures and mean reliability functions. We then discuss some stochastic comparisons of residual lives between two systems based on the stochastic ordering of coefficient vectors （or components） of the two systems. These results form nice extensions of some known results for the case of independent and identically distributed components.
文摘This letter analyzes the outage probability of opportunistic amplify-and-forward relaying over asymmetric and independent but non-identically distributed (i.n.d) fading environments. The work investigates the scenarios where cooperative nodes are located at different geographical locations. As a result, the different signals are affected by different i.n.d fading channels, one may undergo Rician fading distribution and others may undergo Rayleigh fading distribution. In this letter, a lower bound of the outage probability for various asymmetric fading environments is derived at high SNR by applying the initial value theorem. The analytical model is validated through Monte-Carlo simulation results.
