The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning...The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning being difficult to process large-scale unlabeled data. The existing federated self-supervision framework has problems with low communication efficiency and high communication delay between clients and central servers. Therefore, we added edge servers to the federated self-supervision framework to reduce the pressure on the central server caused by frequent communication between both ends. A communication compression scheme using gradient quantization and sparsification was proposed to optimize the communication of the entire framework, and the algorithm of the sparse communication compression module was improved. Experiments have proved that the learning rate changes of the improved sparse communication compression module are smoother and more stable. Our communication compression scheme effectively reduced the overall communication overhead.展开更多
Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of t...Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of the real‐word system are multiple relations,where entities are linked by different types of relations,and each relation is a view of the graph network.Second,the rich multi‐scale information(structure‐level and feature‐level)of the graph network can be seen as self‐supervised signals,which are not fully exploited.A novel contrastive self‐supervised representation learning framework on attributed multiplex graph networks with multi‐scale(named CoLM^(2)S)information is presented in this study.It mainly contains two components:intra‐relation contrast learning and interrelation contrastive learning.Specifically,the contrastive self‐supervised representation learning framework on attributed single‐layer graph networks with multi‐scale information(CoLMS)framework with the graph convolutional network as encoder to capture the intra‐relation information with multi‐scale structure‐level and feature‐level selfsupervised signals is introduced first.The structure‐level information includes the edge structure and sub‐graph structure,and the feature‐level information represents the output of different graph convolutional layer.Second,according to the consensus assumption among inter‐relations,the CoLM^(2)S framework is proposed to jointly learn various graph relations in attributed multiplex graph network to achieve global consensus node embedding.The proposed method can fully distil the graph information.Extensive experiments on unsupervised node clustering and graph visualisation tasks demonstrate the effectiveness of our methods,and it outperforms existing competitive baselines.展开更多
This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorith...This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorithm was used for the training of the linking-weights of the neural network.Hence it gets rid of the difficulty of choosing these tuning-knobs manually and provides easier condition for the wide applications of GPC on industrial plants.Simulation results illustrated the effectiveness of the method.展开更多
The relation between structures and properties of polyurethane are investigated by modern physical and chemical methods.The results obtained are as follows:the effects of the content of self-crosslinking agent on the ...The relation between structures and properties of polyurethane are investigated by modern physical and chemical methods.The results obtained are as follows:the effects of the content of self-crosslinking agent on the properties of polyurethane,i.e.,dispersion stability,dynamical viscoelasticity and mechanical properties are discussed.It is found that the optimum molar ratio of epichlorohydrin and diethylenetriamine is 1:2.A mois-展开更多
The Belt and Road Initiative contains the aspiration of Chinese nation to pursue ideological freedom and desire of strengthening international exchanges and cooperation. This paper takes the Belt and Road Initiative f...The Belt and Road Initiative contains the aspiration of Chinese nation to pursue ideological freedom and desire of strengthening international exchanges and cooperation. This paper takes the Belt and Road Initiative for example,emphasizing the interpretation of the inheritance and development of Chinese culture so as to study the importance of Culture Self-Consciousness in Chinese Philosophy,in the context of English globalization. That is to say,this paper stresses the spirits and the stand of nation 's demonstration on pursuing peace,cooperation and sustainable development in the civilization continuity from traditional China to the contemporary China,with practical philosophic view.展开更多
文摘The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning being difficult to process large-scale unlabeled data. The existing federated self-supervision framework has problems with low communication efficiency and high communication delay between clients and central servers. Therefore, we added edge servers to the federated self-supervision framework to reduce the pressure on the central server caused by frequent communication between both ends. A communication compression scheme using gradient quantization and sparsification was proposed to optimize the communication of the entire framework, and the algorithm of the sparse communication compression module was improved. Experiments have proved that the learning rate changes of the improved sparse communication compression module are smoother and more stable. Our communication compression scheme effectively reduced the overall communication overhead.
基金support by the National Natural Science Foundation of China(NSFC)under grant number 61873274.
文摘Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of the real‐word system are multiple relations,where entities are linked by different types of relations,and each relation is a view of the graph network.Second,the rich multi‐scale information(structure‐level and feature‐level)of the graph network can be seen as self‐supervised signals,which are not fully exploited.A novel contrastive self‐supervised representation learning framework on attributed multiplex graph networks with multi‐scale(named CoLM^(2)S)information is presented in this study.It mainly contains two components:intra‐relation contrast learning and interrelation contrastive learning.Specifically,the contrastive self‐supervised representation learning framework on attributed single‐layer graph networks with multi‐scale information(CoLMS)framework with the graph convolutional network as encoder to capture the intra‐relation information with multi‐scale structure‐level and feature‐level selfsupervised signals is introduced first.The structure‐level information includes the edge structure and sub‐graph structure,and the feature‐level information represents the output of different graph convolutional layer.Second,according to the consensus assumption among inter‐relations,the CoLM^(2)S framework is proposed to jointly learn various graph relations in attributed multiplex graph network to achieve global consensus node embedding.The proposed method can fully distil the graph information.Extensive experiments on unsupervised node clustering and graph visualisation tasks demonstrate the effectiveness of our methods,and it outperforms existing competitive baselines.
文摘Self-Training算法的性能很大程度上取决于高置信度样本的识别准确度。受DPC算法启发,利用密度峰值定义样本间的原型关系,并构造出近亲结点图这一新型数据结构。在此基础上,提出了一种近亲结点图编辑的Self Training算法(self-training algorithm with editing direct relative node graph-DRNG)。DRNG采用假设检验的方法选择高置信度样本,将其加入有标签样本集进行迭代训练。因误分的高密度样本点对Self-Training算法的分类性能影响较大,所以,DRNG综合考虑距离和密度两个方面定义了近亲结点图中割边的非对称权重,增大了高密度点的割边权重,使其落在拒绝域外的概率增加,减小了因其误分类而产生的风险。为了验证DRNG的性能,在8个基准数据集上与类似算法进行对比实验,实验结果验证了DRNG的有效性。
基金Supported by the National 863 CIMS Project Foundation(863-511-010)Tianjin Natural Science Foundation(983602011)Backbone Young Teacher Project Foundation of Ministry of Education
文摘This paper describes the self—adjustment of some tuning-knobs of the generalized predictive controller(GPC).A three feedforward neural network was utilized to on line learn two key tuning-knobs of GPC,and BP algorithm was used for the training of the linking-weights of the neural network.Hence it gets rid of the difficulty of choosing these tuning-knobs manually and provides easier condition for the wide applications of GPC on industrial plants.Simulation results illustrated the effectiveness of the method.
文摘The relation between structures and properties of polyurethane are investigated by modern physical and chemical methods.The results obtained are as follows:the effects of the content of self-crosslinking agent on the properties of polyurethane,i.e.,dispersion stability,dynamical viscoelasticity and mechanical properties are discussed.It is found that the optimum molar ratio of epichlorohydrin and diethylenetriamine is 1:2.A mois-
文摘The Belt and Road Initiative contains the aspiration of Chinese nation to pursue ideological freedom and desire of strengthening international exchanges and cooperation. This paper takes the Belt and Road Initiative for example,emphasizing the interpretation of the inheritance and development of Chinese culture so as to study the importance of Culture Self-Consciousness in Chinese Philosophy,in the context of English globalization. That is to say,this paper stresses the spirits and the stand of nation 's demonstration on pursuing peace,cooperation and sustainable development in the civilization continuity from traditional China to the contemporary China,with practical philosophic view.
