For networking of big data applications,an essential issue is how to represent networks in vector space for further mining and analysis tasks,e.g.,node classification,clustering,link prediction,and visualization.Most ...For networking of big data applications,an essential issue is how to represent networks in vector space for further mining and analysis tasks,e.g.,node classification,clustering,link prediction,and visualization.Most existing studies on this subject mainly concentrate on monoplex networks considering a single type of relation among nodes.However,numerous real-world networks are naturally composed of multiple layers with different relation types;such a network is called a multiplex network.The majority of existing multiplex network embedding methods either overlook node attributes,resort to node labels for training,or underutilize underlying information shared across multiple layers.In this paper,we propose Multiplex Network Infomax(MNI),an unsupervised embedding framework to represent information of multiple layers into a unified embedding space.To be more specific,we aim to maximize the mutual information between the unified embedding and node embeddings of each layer.On the basis of this framework,we present an unsupervised network embedding method for attributed multiplex networks.Experimental results show that our method achieves competitive performance on not only node-related tasks,such as node classification,clustering,and similarity search,but also a typical edge-related task,i.e.,link prediction,at times even outperforming relevant supervised methods,despite that MNI is fully unsupervised.展开更多
The article gives Professor Wei’s experience of using theory of mutual reinforce-ing therapies in acupuncture and moxibustion on treating asthma. There are different 8 kinds of thera-pies such as acupuncture, plum-bl...The article gives Professor Wei’s experience of using theory of mutual reinforce-ing therapies in acupuncture and moxibustion on treating asthma. There are different 8 kinds of thera-pies such as acupuncture, plum-blossom needles, embedding of catgut in point, cupping on Ashipoint, external application on points, suppurative moxibustion, injection in points, etc. All of thesemethods have both advantages and backdraws. Prof. Wei tells us how to make full use of them, sothat we are able to improve the curative effect to its possible extend. This theory is important not onlyin acupuncture and moxibustion but also in guiding our practice in other fields of T. C. M.展开更多
为探究非规则颗粒级配分布对杂填土地基互嵌沉降的影响,借助自主研制的杂填土与软土互嵌试验仪,通过室内试验分析杂填土地基试样的互嵌沉降和软土固结沉降,研究级配不同的3种杂填土地基试样在不同上覆荷载(50、100、150 k Pa)作用下的...为探究非规则颗粒级配分布对杂填土地基互嵌沉降的影响,借助自主研制的杂填土与软土互嵌试验仪,通过室内试验分析杂填土地基试样的互嵌沉降和软土固结沉降,研究级配不同的3种杂填土地基试样在不同上覆荷载(50、100、150 k Pa)作用下的总沉降、互嵌沉降的发展规律及互嵌沉降和总沉降之间的关系,探究曲率系数和上覆荷载变化对杂填土地基试样稳定沉降量的影响.试验结果表明:级配不同的3种杂填土地基试样的总沉降和互嵌沉降时程曲线均可划分为线性增长、缓慢上升、趋于稳定3个阶段.互嵌沉降是杂填土地基试样沉降的主要组成部分,特别是在互嵌发展的初期.当上覆荷载较小(50 kPa)时,杂填土地基试样的稳定沉降量随杂填土曲率系数的增大先增大后减小;当上覆荷载较大(100 k Pa和150 kPa)时,杂填土地基试样的稳定沉降量随杂填土曲率系数的增大先减小后增大.展开更多
详细介绍了一种新的机器学习的方法——流形学习。流形学习是一种新的非监督学习方法,可以有效地发现高维非线性数据集的内在维数并进行维数约简,近年来越来越受到机器学习和认知科学领域的研究者的重视。目前已经出现了很多有效的流形...详细介绍了一种新的机器学习的方法——流形学习。流形学习是一种新的非监督学习方法,可以有效地发现高维非线性数据集的内在维数并进行维数约简,近年来越来越受到机器学习和认知科学领域的研究者的重视。目前已经出现了很多有效的流形学习算法,如等度规映射(ISOMAP)、局部线性嵌套(Locally Linear Embedding,LLE)等。详细讲述了当前常用的几种流形学习算法以及在流形方面已经取得的研究成果,并对流形学习目前在各方面的应用作了较为细致的阐述。最后展望了流形学习的研究发展趋势,且提出了流形学习中仍需解决的关键问题。展开更多
基金This work was supported by the National Natural Science Foundation of China(NSFC)under Grant U19B2004in part by National Key R&D Program of China under Grant 2022YFB2901202+1 种基金in part by the Open Funding Projects of the State Key Laboratory of Communication Content Cognition(No.20K05 and No.A02107)in part by the Special Fund for Science and Technology of Guangdong Province under Grant 2019SDR002.
文摘For networking of big data applications,an essential issue is how to represent networks in vector space for further mining and analysis tasks,e.g.,node classification,clustering,link prediction,and visualization.Most existing studies on this subject mainly concentrate on monoplex networks considering a single type of relation among nodes.However,numerous real-world networks are naturally composed of multiple layers with different relation types;such a network is called a multiplex network.The majority of existing multiplex network embedding methods either overlook node attributes,resort to node labels for training,or underutilize underlying information shared across multiple layers.In this paper,we propose Multiplex Network Infomax(MNI),an unsupervised embedding framework to represent information of multiple layers into a unified embedding space.To be more specific,we aim to maximize the mutual information between the unified embedding and node embeddings of each layer.On the basis of this framework,we present an unsupervised network embedding method for attributed multiplex networks.Experimental results show that our method achieves competitive performance on not only node-related tasks,such as node classification,clustering,and similarity search,but also a typical edge-related task,i.e.,link prediction,at times even outperforming relevant supervised methods,despite that MNI is fully unsupervised.
文摘The article gives Professor Wei’s experience of using theory of mutual reinforce-ing therapies in acupuncture and moxibustion on treating asthma. There are different 8 kinds of thera-pies such as acupuncture, plum-blossom needles, embedding of catgut in point, cupping on Ashipoint, external application on points, suppurative moxibustion, injection in points, etc. All of thesemethods have both advantages and backdraws. Prof. Wei tells us how to make full use of them, sothat we are able to improve the curative effect to its possible extend. This theory is important not onlyin acupuncture and moxibustion but also in guiding our practice in other fields of T. C. M.
文摘为探究非规则颗粒级配分布对杂填土地基互嵌沉降的影响,借助自主研制的杂填土与软土互嵌试验仪,通过室内试验分析杂填土地基试样的互嵌沉降和软土固结沉降,研究级配不同的3种杂填土地基试样在不同上覆荷载(50、100、150 k Pa)作用下的总沉降、互嵌沉降的发展规律及互嵌沉降和总沉降之间的关系,探究曲率系数和上覆荷载变化对杂填土地基试样稳定沉降量的影响.试验结果表明:级配不同的3种杂填土地基试样的总沉降和互嵌沉降时程曲线均可划分为线性增长、缓慢上升、趋于稳定3个阶段.互嵌沉降是杂填土地基试样沉降的主要组成部分,特别是在互嵌发展的初期.当上覆荷载较小(50 kPa)时,杂填土地基试样的稳定沉降量随杂填土曲率系数的增大先增大后减小;当上覆荷载较大(100 k Pa和150 kPa)时,杂填土地基试样的稳定沉降量随杂填土曲率系数的增大先减小后增大.
文摘详细介绍了一种新的机器学习的方法——流形学习。流形学习是一种新的非监督学习方法,可以有效地发现高维非线性数据集的内在维数并进行维数约简,近年来越来越受到机器学习和认知科学领域的研究者的重视。目前已经出现了很多有效的流形学习算法,如等度规映射(ISOMAP)、局部线性嵌套(Locally Linear Embedding,LLE)等。详细讲述了当前常用的几种流形学习算法以及在流形方面已经取得的研究成果,并对流形学习目前在各方面的应用作了较为细致的阐述。最后展望了流形学习的研究发展趋势,且提出了流形学习中仍需解决的关键问题。
