Computer Science ›› 2022, Vol. 49 ›› Issue (7): 254-262.doi: 10.11896/jsjkx.210600184

• Computer Network • Previous Articles     Next Articles

Multi-task Cooperative Optimization Algorithm Based on Adaptive Knowledge Transfer andResource Allocation

TANG Feng, FENG Xiang, YU Hui-qun   

  1. School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China
    Shanghai Engineering Research Center of Smart Energy,Shanghai 200237,China
  • Received:2021-06-28 Revised:2021-10-18 Online:2022-07-15 Published:2022-07-12
  • About author:TANG Feng,born in 1997,postgra-duate.Her main research interests include evolutionary computation and swarm intelligence.
    FENG Xiang,born in 1977,Ph.D,professor,is a member of China Computer Federation.Her main research interests include artificial intelligence,swarm intelligence and evolutionary computing,and big data intelligence.
  • Supported by:
    National Natural Science Foundation of China(61772200,61772201,61602175),Shanghai Pujiang Talent Program(17PJ1401900) and Shanghai Economic and Information Commission “Special Fund for Information Development”(201602008).

Abstract: Multi-task optimization algorithm optimizes each task separately and transfers knowledge among tasks at the same time to improve the comprehensive performance of multiple tasks.However,the negative knowledge transfer between tasks with low similarity leads to the overall performance degradation,and allocating the same computing resources to tasks with different difficulties will lead to resource waste.In addition,it is easy to fall into local optimum by using fixed search step size at different stages of the task.To solve these problems,a multi-task collaborative optimization(AMTO) algorithm based on adaptive know-ledge transfer and dynamic resource allocation is proposed.Firstly,each task is optimized by a single population,and a population is divided into three subpopulations.Three different search strategies are adopted to increase the diversity of search behavior.The search step size is dynamically updated according to the individual update success rate in a single task to enhance the adaptive search ability and avoid falling into local optimum.Secondly,the similarity between tasks is calculated online using the feedback results of knowledge transfer among multiple tasks,and the transfer probability is adjusted adaptively according to the similarity.At the same time,when the similarity between tasks is low,the task deviation should be subtracted to reduce the performance degradation caused by negative knowledge transfer and improve the perception ability of the algorithm to the differences between tasks.Then,the difficulty and optimization state of the task is estimated by evaluating the improvement degree of the task performance,and the resources are dynamically allocated on demand for the tasks with different difficulties and states to maximize the utilization value of resources and reduce the waste of resources.Finally,on the simple and the complex multi-task optimization functions,the proposed algorithm is compared with the classical multi-task algorithms to verify the effectiveness of the adaptive migration strategy,dynamic resource allocation strategy and synthesis.

Key words: Adaptive knowledge transfer, Computing resource allocation, Dynamic group search algorithm, Inter-task deviation, Multi-task collaborative optimization

CLC Number: 

  • TP183
[1]GUPTA A,ONG Y,FENG L.Insights on Transfer Optimization:Because Experience is the Best Teacher[J].IEEE Transactions on Emerging Topics in Computational Intelligence,2017,2(1):51-64.
[2]GUPTA A,ONG Y,FENG L.Multifactorial Evolution:To-wards Evolutionary Multitasking[J].IEEE Transactions on Evo-lutionary Computation,2016,20(3):343-357.
[3]SONG H,QIN A,TSAI P,et al.Multitasking Multi-Swarm Optimization[C]//IEEE Congress on Evolutionary Computation.2019:1937-1944.
[4]FENG L,ZHOU W,ZHOU L,et al.An Empirical Study ofMultifactorial PSO and Multifactorial DE[C]//IEEE Congress on Evolutionary Computation.2017:921-928.
[5]LI G,ZHANG Q,GAO W.Multipopulation Evolution Frame-work for Multifactorial Optimization [C]//Proceedings of the Genetic and Evolutionary Computation Conference Companion.Association for Computing Machinery.2018:215-216.
[6]ZHOU Y,WANG T,PENG X.MFEA-IG:A Multi-Task Algorithm for Mobile Agents Path Planning[C]//IEEE Congress on Evolutionary Computation.2020:1-7.
[7]LIN J,LIU H,TAN K,et al.An Effective Knowledge Transfer Approach for Multiobjective Multitasking Optimization[J].IEEE Transactions on Cybernetics,2021,51(6):3238-3248.
[8]FENG L,HUANG Y,ZHOU L,et al.Explicit EvolutionaryMultitasking for Combinatorial Optimization:A Case Study on Capacitated Vehicle Routing Problem[J].IEEE Transactions on Cybernetics,2021,51(6):3134-3156.
[9]LIN J,LIU H,XUE B,et al.Multiobjective Multitasking Optimization Based on Incremental Learning[J].IEEE Transactions on Evolutionary Computation,2020,24(5):824-838.
[10]DING J,YANG C,JIN Y,et al.Generalized Multi-tasking forEvolutionary Optimization of Expensive Problems[J].IEEE Transactions on Evolutionary Computation,2019,23(1):44-58.
[11]GONG M,TANG Z,LI H,et al.Evolutionary MultitaskingWith Dynamic Resource Allocating Strategy[J].IEEE Transactions on Evolutionary Computation,2019,23(5):858-869.
[12]GUPTA A,ONG Y,FENG L,et al.Multiobjective Multifacto-rial Optimization in Evolutionary Multitasking[J].IEEE Transactions on Cybernetics,2017,47(7):1652-1665.
[13]YUAN Y,ONG Y,FENG L,et al.Evolutionary Multitaskingfor Multiobjective Continuous Optimization:Benchmark Problems,Performance Metrics and Baseline Results[J].arXiv:1706.02766,2017.
[14]LIANG Z,DONG H,LIU W,et al.Evolutionary Multitasking for Multiobjective Optimization With Subspace Alignment and Adaptive Differential Evolution[J].IEEE Transactions on Cybernetics,2020,52(4):2096-2109.
[15]BALI K,GUPTA A,ONG Y,et al.Cognizant Multitasking in Multiobjective Multifactorial Evolution:MO-MFEA-II[J].IEEE Transactions on Cybernetics,2021,51(4):1784-1796.
[16]YI J,BAI J,HE H,et al.A Multifactorial Evolutionary Algorithm for Multitasking Under Interval Uncertainties[J].IEEE Transactions on Evolutionary Computation,2020,24(5):908-922.
[17]SHENG W,WANG X,WANG Z,et al.Adaptive Memetic Differential Evolution with Niching Competition and Supporting Archive Strategies for Multimodal Optimization[J].Information Sciences,2021,573:316-331.
[18]BALI K,ONG Y,GUPTA A,et al.Multifactorial Evolutionary Algorithm with Online Transfer Parameter Estimation:MFEA-II[J].IEEE Transactions on Evolutionary Computation,2020,24(1):69-83.
[19]DA B,ONG Y,FENG L,et al.Evolutionary Multitasking for Single-objective Continuous Optimization:Benchmark Problems,Performance Metric,and Baseline Results[J].arXiv:1706.03470,2017.
[1] WANG Guan-yu, ZHONG Ting, FENG Yu, ZHOU Fan. Collaborative Filtering Recommendation Method Based on Vector Quantization Coding [J]. Computer Science, 2022, 49(9): 48-54.
[2] HUANG Li, ZHU Yan, LI Chun-ping. Author’s Academic Behavior Prediction Based on Heterogeneous Network Representation Learning [J]. Computer Science, 2022, 49(9): 76-82.
[3] NING Han-yang, MA Miao, YANG Bo, LIU Shi-chang. Research Progress and Analysis on Intelligent Cryptology [J]. Computer Science, 2022, 49(9): 288-296.
[4] SHUAI Jian-bo, WANG Jin-ce, HUANG Fei-hu, PENG Jian. Click-Through Rate Prediction Model Based on Neural Architecture Search [J]. Computer Science, 2022, 49(7): 10-17.
[5] DU Hang-yuan, LI Duo, WANG Wen-jian. Method for Abnormal Users Detection Oriented to E-commerce Network [J]. Computer Science, 2022, 49(7): 170-178.
[6] CAI Xin-yu, FENG Xiang, YU Hui-qun. Adaptive Weight Based Broad Learning Algorithm for Cascaded Enhanced Nodes [J]. Computer Science, 2022, 49(6): 134-141.
[7] PU Qian-qian, LEI Hang, LI Zhen-hao, LI Xiao-yu. Personalized News Recommendation Algorithm with Enhanced List Information and User Interests [J]. Computer Science, 2022, 49(6): 142-148.
[8] XIONG Zhong-min, SHU Gui-wen, GUO Huai-yu. Graph Neural Network Recommendation Model Integrating User Preferences [J]. Computer Science, 2022, 49(6): 165-171.
[9] DENG Zhao-yang, ZHONG Guo-qiang, WANG Dong. Text Classification Based on Attention Gated Graph Neural Network [J]. Computer Science, 2022, 49(6): 326-334.
[10] DU Li-jun, TANG Xi-lu, ZHOU Jiao, CHEN Yu-lan, CHENG Jian. Alzheimer's Disease Classification Method Based on Attention Mechanism and Multi-task Learning [J]. Computer Science, 2022, 49(6A): 60-65.
[11] LIU Bao-bao, YANG Jing-jing, TAO Lu, WANG He-ying. Study on Prediction of Educational Statistical Data Based on DE-LSTM Model [J]. Computer Science, 2022, 49(6A): 261-266.
[12] ZHOU Zhi-hao, CHEN Lei, WU Xiang, QIU Dong-liang, LIANG Guang-sheng, ZENG Fan-qiao. SMOTE-SDSAE-SVM Based Vehicle CAN Bus Intrusion Detection Algorithm [J]. Computer Science, 2022, 49(6A): 562-570.
[13] WANG Jian. Back-propagation Neural Network Learning Algorithm Based on Privacy Preserving [J]. Computer Science, 2022, 49(6A): 575-580.
[14] WANG Shan, XU Chu-yi, SHI Chun-xiang, ZHANG Ying. Study on Cloud Classification Method of Satellite Cloud Images Based on CNN-LSTM [J]. Computer Science, 2022, 49(6A): 675-679.
[15] WANG Fei, HUANG Tao, YANG Ye. Study on Machine Learning Algorithms for Life Prediction of IGBT Devices Based on Stacking Multi-model Fusion [J]. Computer Science, 2022, 49(6A): 784-789.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!