Intelligent fitting global real‐time task scheduling strategy for high‐performance multi‐core systems

Wu, Jian; Zhao, Enyuan; Li, Sizhao; Wang, Yanqiang

doi:10.1049/cit2.12063

Cited by 7 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to solve the above problems, we further explore the influence of individual local model updating on the fairness coefficient and update the model more reasonably. q k is used to update the model parameters of corresponding clients, and we call this fine-grained approach Ada-IFFL Equation (6).…”

Section: Algorithm 2 Ada-ifflmentioning

confidence: 99%

“…On the basis of Ada-GFFL and Ada-IFFL, we apply Equation (7) to Equation ( 5) and Equation (6) and propose new adaptive polymerisation methods Ada-G r FFL and Ada-I r FFL. The objective function is shown in Equations ( 8) and ( 9).…”

Section: Adaptive Fairness Federated Learning: Ada-fflmentioning

confidence: 99%

“…Researchers have considered the aggregation scheme of federated learning to control client performance [6] in federated learning. McMaha proposed a weighted average aggregation algorithm FedAvg based on the number of client samples [4].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Ada‐FFL: Adaptive computing fairness federated learning

Cong

Qiu

Zhang

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

As the scale of federated learning expands, solving the Non‐IID data problem of federated learning has become a key challenge of interest. Most existing solutions generally aim to solve the overall performance improvement of all clients; however, the overall performance improvement often sacrifices the performance of certain clients, such as clients with less data. Ignoring fairness may greatly reduce the willingness of some clients to participate in federated learning. In order to solve the above problem, the authors propose Ada‐FFL, an adaptive fairness federated aggregation learning algorithm, which can dynamically adjust the fairness coefficient according to the update of the local models, ensuring the convergence performance of the global model and the fairness between federated learning clients. By integrating coarse‐grained and fine‐grained equity solutions, the authors evaluate the deviation of local models by considering both global equity and individual equity, then the weight ratio will be dynamically allocated for each client based on the evaluated deviation value, which can ensure that the update differences of local models are fully considered in each round of training. Finally, by combining a regularisation term to limit the local model update to be closer to the global model, the sensitivity of the model to input perturbations can be reduced, and the generalisation ability of the global model can be improved. Through numerous experiments on several federal data sets, the authors show that our method has more advantages in convergence effect and fairness than the existing baselines.

show abstract

Section: Algorithm 2 Ada-ifflmentioning

confidence: 99%

Section: Adaptive Fairness Federated Learning: Ada-fflmentioning

confidence: 99%

See 1 more Smart Citation

Ada‐FFL: Adaptive computing fairness federated learning

Cong

Qiu

Zhang

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

show abstract

“…For example, for the solution of non-linear equations with many variables, which also contain matrix inversion, the cost of taking direct methods is too high, and iterative methods are usually used. Note that, although the majority of existing algorithms deal with static problems, in reality [4][5][6], time-varying systems and problems frequently develop, making conventional algorithms inapplicable.…”

Section: Introductionmentioning

confidence: 99%

An advanced discrete‐time RNN for handling discrete time‐varying matrix inversion: Form model design to disturbance‐suppression analysis

Shi

Cao

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Time‐varying matrix inversion is an important field of matrix research, and lots of research achievements have been obtained. In the process of solving time‐varying matrix inversion, disturbances inevitably exist, thus, a model that can suppress disturbance while solving the problem is required. In this paper, an advanced continuous‐time recurrent neural network (RNN) model based on a double integral RNN design formula is proposed for solving continuous time‐varying matrix inversion, which has incomparable disturbance‐suppression property. For digital hardware applications, the corresponding advanced discrete‐time RNN model is proposed based on the discretisation formulas. As a result of theoretical analysis, it is demonstrated that the advanced continuous‐time RNN model and the corresponding advanced discrete‐time RNN model have global and exponential convergence performance, and they are excellent for suppressing different disturbances. Finally, inspiring experiments, including two numerical experiments and a practical experiment, are presented to demonstrate the effectiveness and superiority of the advanced discrete‐time RNN model for solving discrete time‐varying matrix inversion with disturbance‐suppression.

show abstract

The quality evaluation system of ideological and political classroom teaching in universities based on GA‐BP algorithm

Jing

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe advancement of teaching quality is an indispensable section of the reform and growth of universities, and ideological and political education has critical impact on ideological education. The quality of classroom education can provide data support for efficient development, and has crucial influence on achieving scientific, reasonable, and accurate evaluation of ideological and political teaching performance. Thus, a performance assessment system for ideological and political education in universities with genetic algorithm optimized neural network algorithm is put forward. First, based on existing teaching evaluation indicators and combined with actual situations, a targeted teaching quality evaluation system is proposed. Then, based on BP, an adaptive genetic algorithm is proposed for improvement, and the output results are improved using entropy method. The results indicated that the proposed model could reach its optimal state after 81 iterations in this study. In the fitting test, it reached 0.971. In actual testing, the average error was only 2.68, which was much bigger than the other three algorithms. Its accuracy was 2%–3.2% higher than that of the best existing algorithms. These results indicated that the method put forward in this study had better practical significance, lower error, more accurate evaluation results, and offered scientific data support for the education reform work of universities, which can better accelerate the development and construction of universities.

show abstract

Intelligent fitting global real‐time task scheduling strategy for high‐performance multi‐core systems

Cited by 7 publications

References 27 publications

Ada‐FFL: Adaptive computing fairness federated learning

Ada‐FFL: Adaptive computing fairness federated learning

An advanced discrete‐time RNN for handling discrete time‐varying matrix inversion: Form model design to disturbance‐suppression analysis

The quality evaluation system of ideological and political classroom teaching in universities based on GA‐BP algorithm

Contact Info

Product

Resources

About