In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations a...In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.展开更多
智能反射表面(Intelligent Reflecting Surface,IRS)能够对入射其上的信号进行一定的相位和幅度的变换,从而达到信号的精确传输,提高信号的覆盖和传输效率。但是这种优势都是在已知精确的信道状态信息(Channel State Information,CSI)...智能反射表面(Intelligent Reflecting Surface,IRS)能够对入射其上的信号进行一定的相位和幅度的变换,从而达到信号的精确传输,提高信号的覆盖和传输效率。但是这种优势都是在已知精确的信道状态信息(Channel State Information,CSI)的前提下才能达到。基于IRS元件的无源性,精确的CSI很难得到。针对此问题使用压缩感知(Compressive Sensing,CS)算法结合深度学习(Deep Learning,DL)的方法来解决。使用共链路结构来优化传统的压缩感知算法,能够在更低的导频开销和信噪比(Signal to Noise Ratio,SNR)下获得更好的归一化均方误差(Normalized Mean Square Error,NMSE)。将信道估计问题看作为去噪问题,把优化后的CS算法所得结果看作含有噪声的CSI,使用多重深层降噪块网络对其进一步去噪,得到更加精确的CSI。实验表明,所提算法较对比算法在相同SNR下有更好的精度。展开更多
链路预测是利用深度学习技术分析网络数据,挖掘网络中潜在的节点关系,通常应用于网络安全、信息挖掘等领域。通过预测网络中节点间的链路,可以识别社交工程攻击、欺诈行为和隐私泄露风险。但移动社交网络的拓扑结构随时间变化,链路稀疏...链路预测是利用深度学习技术分析网络数据,挖掘网络中潜在的节点关系,通常应用于网络安全、信息挖掘等领域。通过预测网络中节点间的链路,可以识别社交工程攻击、欺诈行为和隐私泄露风险。但移动社交网络的拓扑结构随时间变化,链路稀疏,影响预测准确性。为了解决移动社交网络中链路预测的强稀疏性问题,提出基于深度学习的预测方法,即面向强稀疏性移动社交网络的链路预测深度学习方法(deep learning-based method for mobile social networks with strong sparsity for link prediction,DLMSS-LP)。该方法综合运用了图自编码器(graph auto-encoder,GAE)、特征矩阵聚合技术以及多层长短期记忆网络(long short-term memory,LSTM),旨在降低了模型的学习成本,更有效地处理高维和非线性的网络结构,并且捕捉移动社交网络中的时序动态变化,进而增强模型对现有链路生成可能性的预测能力。对比其他方法在AUC(area under curve)和ER(error rate)指标上有明显提升,体现了模型对不确定链路预测的高准确率和强鲁棒性。展开更多
文摘In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.
文摘智能反射表面(Intelligent Reflecting Surface,IRS)能够对入射其上的信号进行一定的相位和幅度的变换,从而达到信号的精确传输,提高信号的覆盖和传输效率。但是这种优势都是在已知精确的信道状态信息(Channel State Information,CSI)的前提下才能达到。基于IRS元件的无源性,精确的CSI很难得到。针对此问题使用压缩感知(Compressive Sensing,CS)算法结合深度学习(Deep Learning,DL)的方法来解决。使用共链路结构来优化传统的压缩感知算法,能够在更低的导频开销和信噪比(Signal to Noise Ratio,SNR)下获得更好的归一化均方误差(Normalized Mean Square Error,NMSE)。将信道估计问题看作为去噪问题,把优化后的CS算法所得结果看作含有噪声的CSI,使用多重深层降噪块网络对其进一步去噪,得到更加精确的CSI。实验表明,所提算法较对比算法在相同SNR下有更好的精度。
文摘链路预测是利用深度学习技术分析网络数据,挖掘网络中潜在的节点关系,通常应用于网络安全、信息挖掘等领域。通过预测网络中节点间的链路,可以识别社交工程攻击、欺诈行为和隐私泄露风险。但移动社交网络的拓扑结构随时间变化,链路稀疏,影响预测准确性。为了解决移动社交网络中链路预测的强稀疏性问题,提出基于深度学习的预测方法,即面向强稀疏性移动社交网络的链路预测深度学习方法(deep learning-based method for mobile social networks with strong sparsity for link prediction,DLMSS-LP)。该方法综合运用了图自编码器(graph auto-encoder,GAE)、特征矩阵聚合技术以及多层长短期记忆网络(long short-term memory,LSTM),旨在降低了模型的学习成本,更有效地处理高维和非线性的网络结构,并且捕捉移动社交网络中的时序动态变化,进而增强模型对现有链路生成可能性的预测能力。对比其他方法在AUC(area under curve)和ER(error rate)指标上有明显提升,体现了模型对不确定链路预测的高准确率和强鲁棒性。
