Centralized training of deep learning models poses privacy risks that hinder their deployment.Federated learning(FL)has emerged as a solution to address these risks,allowing multiple clients to train deep learning mod...Centralized training of deep learning models poses privacy risks that hinder their deployment.Federated learning(FL)has emerged as a solution to address these risks,allowing multiple clients to train deep learning models collaborativelywithout sharing rawdata.However,FL is vulnerable to the impact of heterogeneous distributed data,which weakens convergence stability and suboptimal performance of the trained model on local data.This is due to the discarding of the old local model at each round of training,which results in the loss of personalized information in the model critical for maintaining model accuracy and ensuring robustness.In this paper,we propose FedTC,a personalized federated learning method with two classifiers that can retain personalized information in the local model and improve the model’s performance on local data.FedTC divides the model into two parts,namely,the extractor and the classifier,where the classifier is the last layer of the model,and the extractor consists of other layers.The classifier in the local model is always retained to ensure that the personalized information is not lost.After receiving the global model,the local extractor is overwritten by the globalmodel’s extractor,and the classifier of the globalmodel serves as anadditional classifier of the localmodel toguide local training.The FedTCintroduces a two-classifier training strategy to coordinate the two classifiers for local model updates.Experimental results on Cifar10 and Cifar100 datasets demonstrate that FedTC performs better on heterogeneous data than current studies,such as FedAvg,FedPer,and local training,achieving a maximum improvement of 27.95%in model classification test accuracy compared to FedAvg.展开更多
Developing highly efficient bifunctional cathode and anode electrocatalysts is very important for the large-scale application of direct formic acid fuel cells. However, the high-cost and poor CO-tolera nee ability of ...Developing highly efficient bifunctional cathode and anode electrocatalysts is very important for the large-scale application of direct formic acid fuel cells. However, the high-cost and poor CO-tolera nee ability of the most commonly used Pt greatly block this process. To in crease the utilizatio n efficie ncy and exte nd bifunctional properties of precious Pt, herei n, coral-like Pt3Ag nano crystals are developed as an excelle nt bifunctional electrocatalyst through a facile one-pot solvothermal method. The formation mechanism of Ptgg nanocorals has been elaborated well via a series of control experiments. It is proved that 1-naphthol serving as a guiding surfactant plays a key role in the formation of high-quality nano corals. Thanks to the unique coral-like structure and alloy effects, the developed Ptgg nano corals present sign ificantly enhanced electrocatalytic properties (including activity, stability and CO-toleranee ability) towards both the cathodic oxygen reduction and anodic formic acid oxidati on, as compared with those of commercial Pt black and Pt-based nan oparticles. The prese nt synthetic method can also be extended to fabricate other bimetallic electrocatalysts with unique morphology and structure.展开更多
Weighted complex dynamical networks with heterogeneous delays in both continuous-time and discrete-time domains are controlled by applying local feedback injections to a small fraction of network nodes. Some generic s...Weighted complex dynamical networks with heterogeneous delays in both continuous-time and discrete-time domains are controlled by applying local feedback injections to a small fraction of network nodes. Some generic stability criteria ensuring delay-independent stability are derived for such controlled networks in terms of linear matrix inequalities （LMIs）, which guarantee that by placing a small number of feedback controllers on some nodes the whole network can be pinned to some desired homogenous states. In some particular cases, a single controller can achieve the control objective. It is found that stabilization of such pinned networks is completely determined by the dynamics of the individual uncoupled node, the overall coupling strength, the inner-coupling matrix, and the smallest eigenvalue of the coupling and control matrix. Numerical simulations of a weighted network composing of a 3-dimensional nonlinear system are finally given for illustration and verification.展开更多
基金funded by Shenzhen Basic Research(Key Project)(No.JCYJ20200109113405927)Shenzhen Stable Supporting Program(General Project)(No.GXWD20201230155427003-20200821160539001)+1 种基金Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies(2022B1212010005)Peng Cheng Laboratory Project(Grant No.PCL2021A02),Ministry of Education’s Collaborative Education Project with Industry Cooperation(No.22077141140831).
文摘Centralized training of deep learning models poses privacy risks that hinder their deployment.Federated learning(FL)has emerged as a solution to address these risks,allowing multiple clients to train deep learning models collaborativelywithout sharing rawdata.However,FL is vulnerable to the impact of heterogeneous distributed data,which weakens convergence stability and suboptimal performance of the trained model on local data.This is due to the discarding of the old local model at each round of training,which results in the loss of personalized information in the model critical for maintaining model accuracy and ensuring robustness.In this paper,we propose FedTC,a personalized federated learning method with two classifiers that can retain personalized information in the local model and improve the model’s performance on local data.FedTC divides the model into two parts,namely,the extractor and the classifier,where the classifier is the last layer of the model,and the extractor consists of other layers.The classifier in the local model is always retained to ensure that the personalized information is not lost.After receiving the global model,the local extractor is overwritten by the globalmodel’s extractor,and the classifier of the globalmodel serves as anadditional classifier of the localmodel toguide local training.The FedTCintroduces a two-classifier training strategy to coordinate the two classifiers for local model updates.Experimental results on Cifar10 and Cifar100 datasets demonstrate that FedTC performs better on heterogeneous data than current studies,such as FedAvg,FedPer,and local training,achieving a maximum improvement of 27.95%in model classification test accuracy compared to FedAvg.
基金the National Natural Science Foundation of China (Nos. 21576139, 21875112, 21576050 and 51602052)Jiangsu Provincial Natural Science Foundation of China (No. BK20150604)+1 种基金National and Local Joint Engineering Research Center of Biomedical Functional MaterialsPriority Academic Program Development of Jiangsu Higher Education Institutions.
文摘Developing highly efficient bifunctional cathode and anode electrocatalysts is very important for the large-scale application of direct formic acid fuel cells. However, the high-cost and poor CO-tolera nee ability of the most commonly used Pt greatly block this process. To in crease the utilizatio n efficie ncy and exte nd bifunctional properties of precious Pt, herei n, coral-like Pt3Ag nano crystals are developed as an excelle nt bifunctional electrocatalyst through a facile one-pot solvothermal method. The formation mechanism of Ptgg nanocorals has been elaborated well via a series of control experiments. It is proved that 1-naphthol serving as a guiding surfactant plays a key role in the formation of high-quality nano corals. Thanks to the unique coral-like structure and alloy effects, the developed Ptgg nano corals present sign ificantly enhanced electrocatalytic properties (including activity, stability and CO-toleranee ability) towards both the cathodic oxygen reduction and anodic formic acid oxidati on, as compared with those of commercial Pt black and Pt-based nan oparticles. The prese nt synthetic method can also be extended to fabricate other bimetallic electrocatalysts with unique morphology and structure.
基金the National Natural Science Fundation of China (Grant Nos. 60774088 and 60574036)the Specialized Research Fund for the Doctoral Program of Higher Education of China (Grant No. 20050055013)and the Program for New Century Excellent Talents of China (NCET)
文摘Weighted complex dynamical networks with heterogeneous delays in both continuous-time and discrete-time domains are controlled by applying local feedback injections to a small fraction of network nodes. Some generic stability criteria ensuring delay-independent stability are derived for such controlled networks in terms of linear matrix inequalities （LMIs）, which guarantee that by placing a small number of feedback controllers on some nodes the whole network can be pinned to some desired homogenous states. In some particular cases, a single controller can achieve the control objective. It is found that stabilization of such pinned networks is completely determined by the dynamics of the individual uncoupled node, the overall coupling strength, the inner-coupling matrix, and the smallest eigenvalue of the coupling and control matrix. Numerical simulations of a weighted network composing of a 3-dimensional nonlinear system are finally given for illustration and verification.
