Many real-world networks are found to be scale-free. However, graph partition technology, as a technology capable of parallel computing, performs poorly when scale-free graphs are provided. The reason for this is that...Many real-world networks are found to be scale-free. However, graph partition technology, as a technology capable of parallel computing, performs poorly when scale-free graphs are provided. The reason for this is that traditional partitioning algorithms are designed for random networks and regular networks, rather than for scale-free networks. Multilevel graph-partitioning algorithms are currently considered to be the state of the art and are used extensively. In this paper, we analyse the reasons why traditional multilevel graph-partitioning algorithms perform poorly and present a new multilevel graph-partitioning paradigm, top down partitioning, which derives its name from the comparison with the traditional bottom-up partitioning. A new multilevel partitioning algorithm, named betweenness-based partitioning algorithm, is also presented as an implementation of top-down partitioning paradigm. An experimental evaluation of seven different real-world scale-free networks shows that the betweenness-based partitioning algorithm significantly outperforms the existing state-of-the-art approaches.展开更多
微表情检测旨在视频中定位幅度微弱、时间短暂的表情区间。其难点在于有效提取面部区域间的动态关联特征和多尺度时序特征,进而精准捕捉面部各区域微小动作之间的关联。针对这些问题,提出了一种融合自适应图注意力和多尺度可变空洞卷积...微表情检测旨在视频中定位幅度微弱、时间短暂的表情区间。其难点在于有效提取面部区域间的动态关联特征和多尺度时序特征,进而精准捕捉面部各区域微小动作之间的关联。针对这些问题,提出了一种融合自适应图注意力和多尺度可变空洞卷积的微表情检测网络(AG-DDNet)。通过引入参数可学习矩阵来实现键值对的特征变换,通过计算面部区域特征向量间的相似度得到动态邻接矩阵,并结合图注意力机制计算区域间权重系数,实现特征的动态融合;采用了多尺度可变空洞卷积模块,通过自适应池化与卷积组合的预测器生成动态感受野,从而实现多尺度的特征提取;引入基于Fisher信息矩阵的自然梯度优化机制,通过Fisher Adam优化器有效捕捉参数空间的几何结构信息,实现学习率的精确自适应调整,从而显著增强了模型对微表情和宏表情的协同检测能力。在微表情检测任务中,该算法与同类代表性算法相比,在CAS(ME)2数据集和SAMM Long Videos数据集上的性能分别提升了54.20%和20.11%。与最新算法相比,两个数据集上的提升幅度分别为38.43%和6.81%,有效证明了该方法在长视频微表情检测任务上的优越性能。展开更多
现有的电子健康记录(electronic health records,EHR)的图表示学习方法多依赖单个患者的局部信息,忽视了群体患者在疾病演化和诊疗路径上的潜在关联,从而限制了模型的泛化性与鲁棒性.针对这一问题,本文提出一种混合多层级图神经网络(hyb...现有的电子健康记录(electronic health records,EHR)的图表示学习方法多依赖单个患者的局部信息,忽视了群体患者在疾病演化和诊疗路径上的潜在关联,从而限制了模型的泛化性与鲁棒性.针对这一问题,本文提出一种混合多层级图神经网络(hybrid multi-level graph neural network,H-MGNN)模型,并将其应用于重症监护室(intensive care unit,ICU)患者的死亡预测.该模型通过构建宏观层面的患者关系图(patient-patient graph,P-P)、微观层面的分类-笔记-词汇超图(taxonomy-note-word hypergraph,T-N-W),结合超图的时序依赖关系,实现多尺度上的患者特征融合.同时,本文设计了融合算法(hybrid embedding,Hybrid-E),用于提取和整合患者嵌入的潜在特征,以提升预测准确性.实验结果表明,H-MGNN在MIMIC-Ⅲ(medical information mart for intensive care Ⅲ)数据集上的住院死亡率预测等任务中显著优于现有方法,验证了其在复杂EHR数据挖掘中的有效性和先进性.展开更多
基金supported by the National Science Foundation for Distinguished Young Scholars of China(Grant Nos.61003082 and 60903059)the National Natural Science Foundation of China(Grant No.60873014)the Foundation for Innovative Research Groups of the National Natural Science Foundation of China(Grant No.60921062)
文摘Many real-world networks are found to be scale-free. However, graph partition technology, as a technology capable of parallel computing, performs poorly when scale-free graphs are provided. The reason for this is that traditional partitioning algorithms are designed for random networks and regular networks, rather than for scale-free networks. Multilevel graph-partitioning algorithms are currently considered to be the state of the art and are used extensively. In this paper, we analyse the reasons why traditional multilevel graph-partitioning algorithms perform poorly and present a new multilevel graph-partitioning paradigm, top down partitioning, which derives its name from the comparison with the traditional bottom-up partitioning. A new multilevel partitioning algorithm, named betweenness-based partitioning algorithm, is also presented as an implementation of top-down partitioning paradigm. An experimental evaluation of seven different real-world scale-free networks shows that the betweenness-based partitioning algorithm significantly outperforms the existing state-of-the-art approaches.
文摘微表情检测旨在视频中定位幅度微弱、时间短暂的表情区间。其难点在于有效提取面部区域间的动态关联特征和多尺度时序特征,进而精准捕捉面部各区域微小动作之间的关联。针对这些问题,提出了一种融合自适应图注意力和多尺度可变空洞卷积的微表情检测网络(AG-DDNet)。通过引入参数可学习矩阵来实现键值对的特征变换,通过计算面部区域特征向量间的相似度得到动态邻接矩阵,并结合图注意力机制计算区域间权重系数,实现特征的动态融合;采用了多尺度可变空洞卷积模块,通过自适应池化与卷积组合的预测器生成动态感受野,从而实现多尺度的特征提取;引入基于Fisher信息矩阵的自然梯度优化机制,通过Fisher Adam优化器有效捕捉参数空间的几何结构信息,实现学习率的精确自适应调整,从而显著增强了模型对微表情和宏表情的协同检测能力。在微表情检测任务中,该算法与同类代表性算法相比,在CAS(ME)2数据集和SAMM Long Videos数据集上的性能分别提升了54.20%和20.11%。与最新算法相比,两个数据集上的提升幅度分别为38.43%和6.81%,有效证明了该方法在长视频微表情检测任务上的优越性能。
文摘现有的电子健康记录(electronic health records,EHR)的图表示学习方法多依赖单个患者的局部信息,忽视了群体患者在疾病演化和诊疗路径上的潜在关联,从而限制了模型的泛化性与鲁棒性.针对这一问题,本文提出一种混合多层级图神经网络(hybrid multi-level graph neural network,H-MGNN)模型,并将其应用于重症监护室(intensive care unit,ICU)患者的死亡预测.该模型通过构建宏观层面的患者关系图(patient-patient graph,P-P)、微观层面的分类-笔记-词汇超图(taxonomy-note-word hypergraph,T-N-W),结合超图的时序依赖关系,实现多尺度上的患者特征融合.同时,本文设计了融合算法(hybrid embedding,Hybrid-E),用于提取和整合患者嵌入的潜在特征,以提升预测准确性.实验结果表明,H-MGNN在MIMIC-Ⅲ(medical information mart for intensive care Ⅲ)数据集上的住院死亡率预测等任务中显著优于现有方法,验证了其在复杂EHR数据挖掘中的有效性和先进性.
