群体智能中的协作与对抗

doi:10.11896/jsjkx.210900249

摘要/Abstract

摘要： 群体智能有着丰富的内涵和外延,其算法既包括早期基于生物群体特征规律的算法(粒子群优化和蚁群算法等),也包括后期基于网络互联的大规模群体算法(多智能体系统、群智感知和联邦学习等)。这些群体智能算法均蕴含着协作或对抗的核心思想。协作能够把个体的有限智慧耦合汇聚成群体的强大智能,但是协作本身具有一定的局限性,可能会导致个体间过分依赖和系统的不公平性等问题。对抗可以突破这种局限性,其基本思想是个体通过博弈等手段谋取自身最大利益。因此,协作和对抗缺一不可,以对抗促协作,协作中存对抗。通过聚焦群体智能算法的协作和对抗方法,对经典群体智能算法的思想进行阐述,并对新兴的群体智能算法的下一步发展方向进行展望,总结了构建协作与对抗并存的群体智能生态,是群体智能的必然发展趋势。

关键词: 群体智能, 联邦学习, 多智能体系统, 对抗, 博弈

Abstract: Crowd intelligence has rich connotations and denotations.Its algorithms include both the early algorithms based on the characteristics of biological groups(particle swarm optimization,ant colony algorithm,etc.) and the later large-scale crowd algorithms based on network interconnection(multi-agent system,crowd intelligence perception,federated learning,etc.).The core idea of these crowd intelligence algorithms is cooperation or confrontation.Collaboration can combine the limited intelligence of individuals into the powerful intelligence of the group.However,collaboration itself has certain limitations,which may lead to the over-dependence between individuals and the unfairness of the system.Confrontation can overcome this limitation,and its basic idea is that individuals seek their maximum interests through the game.Therefore,cooperation and confrontation are indispensable.It is the inevitable development trend of a crowd intelligence to promote cooperation with confrontation,and to build a crowd intelligence ecology in which cooperation and confrontation coexist.This paper mainly focuses on the cooperation and confrontation methods of crowd intelligence algorithms,expounds on the classical crowd intelligence algorithms,and prospects the next development direction of emerging crowd intelligence algorithms.

Key words: Crowd intelligence, Federated learning, Multi-agent system, Confrontation, Game

中图分类号:

TP191

朱迪迪, 吴超. 群体智能中的协作与对抗[J]. 计算机科学, 2022, 49(11A): 210900249-7. https://doi.org/10.11896/jsjkx.210900249

ZHU Di-di, WU Chao. Cooperation and Confrontation in Crowd Intelligence[J]. Computer Science, 2022, 49(11A): 210900249-7. https://doi.org/10.11896/jsjkx.210900249

参考文献

[1]BENI G.The concept of cellular robotic system[C]//Procee-dings IEEE International Symposium on Intelligent Control 1988.IEEE,1988:57-62
[2]ZHAO J,ZHANG X T,LI J M,et al.Research review of crowd intelligence 2.0 [J].Computer Engineering,2019,45(12):7.
[3]MCMAHAN B,MOORE E,RAMAGE D,et al.Communica-tion-efficient learning of deep networks from decentralized data[C]//Artificial Intelligence and Statistics.PMLR,2017:1273-1282.
[4]DORIGO M,GAMBARDELLA L M.Ant colonies for the traveling salesman problem[J].Biosystems,1997,43(2):73-81.
[5]KENNEDY J,EBERHART R.Particle swarm optimization[C]//ICNN95-International Conference on Neural Networks.2002.
[6]LIU J,CHEN Z Q,LIU Z X.Research Progress of Multi-agent System and its Cooperative Control [J].Journal of Intelligent Systems,2010,5(1):1-9.
[7]LIU Y H.Crowd Sourcing computing[J].Communications ofthe China Computer Federation,2012,8(10):38-41.
[8]SUN J,WANG J,CHEN J,et al.Cooperative communicationbased on swarm intelligence:vision,model,and key technology[J].SCIENTIASINICA Informationis,2020,50(3):307-317.
[9]DUAN H,QIU H.Unmanned aerial vehicle swarm autonomous control based on swarm intelligence[M].Beijing:Science Press,2018.
[10]LAN S F,LIU S.Overview of research on Cuckoo search algorithm[J].Computer Engineering and Design,2015,36(4):1063-1067.
[11]LI X L.A New Intelligent Optimization Method-Artificial Fish School Algorithm [D].Hangzhou:Zhejiang University,2003.
[12]WU H,ZHANG F,WU L.New swarm intelligence algorithm－wolf pack algorithm [J].System Engineering and Electronics,2010,35(11):2430-2438.
[13]ZHANG W,MEI H.A constructive model for collective intelligence[J].National Science Review,2020,7(8):1273-1277.
[14]LITTMAN M L.Markov games as a framework for multi-agentreinforcement learning[C]//Machine Learning Proceedings 1994.Elsevier,1994:157-163.
[15]WU Y,ZENG J R,PENG H,et al.Survey on incentive mechanisms for crowd sensing[J].Ruan Jian Xue Bao/Journal of Softwar,2016,27(8):2025-2047.
[16]DORIGO M,MANIEZZO V,COLORNI A.Ant system:optimization by a colony of cooperating agents[J].IEEE Transactions on Systems,Man,and Cybernetics,Part B(Cybernetics),1996,26(1):29-41.
[17]CLAUS C,BOUTILIER C.The dynamics of reinforcementlearning in cooperative multi-agent systems[C]//Proc. AAAI-98.1998.
[18]SPIROS K,DANIEL K.Reinforcement learning of coordination in cooperative mas[C]//The 18th National Conference on AI.Alberta,Canada:ACM Press.2002:326-331.
[19]YANG Y,LUO R,LI M,et al.Mean field multi-agent reinforcement learning[C]//International Conference on Machine Lear-ning.PMLR,2018:5571-5580.
[20]LIN T,KONG L,STICH S U,et al.Ensemble distillation forrobust model fusion in federated learning[J].arXiv:2006.07242,2020.
[21]HINTON G,VINYALS O,DEAN J.Distilling the knowledge in a neural network[J].arXiv:1503.02531,2015.
[22]NASH J F.Equilibrium points in n-person games[J].Procee-dings of the National Academy of Sciences,1950,36(1):48-49.
[23]HU J,WELLMAN M P.Nash q-learning for general-sum sto-chastic games[J].Journal of Machine Learning Research,2003,4(Nov):1039-1069.
[24]WU Y,ZENG J R,PENG H,et al.Survey on incentive mechanisms for crowd sensing[J].Journal of Software,2016,27(8):2025-2047.
[25]NG K L,CHEN Z,LIU Z,et al.A multi-player game for stu-dying federated learning incentive schemes[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence(IJCAI 2020).2020:5179-5281.
[26]GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial networks[J].arXiv:1406.2661,2014.
[27]JEONG E,OH S,KIM H,et al.Communication-efficient on-device machine learning:Federated distillation and augmentation under non-iid private data[J].arXiv:1811.11479,2018.
[28]AUGENSTEIN S,MCMAHAN H B,RAMAGE D,et al.Ge-nerative models for effective ml on private,decentralized datasets[J].arXiv:1911.06679,2019.
[29]ZHANG J,CHEN J,WU D,et al.Poisoning attack in federated learning using generative adversarial nets[C]//2019 18th IEEE International Conference on Trust,Security and Privacy in Computing And Communications/13th IEEE International Conference On Big Data Science and Engineering(TrustCom/BigDataSE).IEEE,2019:374-380.
[30]ZHAO Y,CHEN J,ZHANG J,et al.Pdgan:a novel poisoning defense method in federated learning using generative adversarialnetwork[C]//International Conference on Algorithms and Architectures for Parallel Processing.Springer,2019:595-609.
[31]RASOULI M,SUN T,RAJAGOPAL R.Fedgan:Federated ge-nerative adversarial networks for distributed data[J].arXiv:2006.07228,2020.
[32]FAN C,LIU P.Federated generative adversarial learning[C]//Chinese Conference on Pattern Recognition and Computer Vision(PRCV).Springer,2020:3-15.
[33]QU H,ZHANG Y,CHANG Q,et al.Learn distributedgan with temporary discriminators[C]//European Conference on Computer Vision.Springer,2020:175-192.
[34]WANG H,KAPLAN Z,NIU D,et al.Optimizing federatedlearning on non-iid data with reinforcement learning[C]//IEEE INFOCOM 2020-IEEE Conference on Computer Communications.IEEE,2020:1698-1707.

相关文章 15

[1]	张佳, 董守斌. 基于评论方面级用户偏好迁移的跨领域推荐算法 Cross-domain Recommendation Based on Review Aspect-level User Preference Transfer 计算机科学, 2022, 49(9): 41-47. https://doi.org/10.11896/jsjkx.220200131
[2]	曹晓雯, 梁美玉, 鲁康康. 基于细粒度语义推理的跨媒体双路对抗哈希学习模型 Fine-grained Semantic Reasoning Based Cross-media Dual-way Adversarial Hashing Learning Model 计算机科学, 2022, 49(9): 123-131. https://doi.org/10.11896/jsjkx.220600011
[3]	鲁晨阳, 邓苏, 马武彬, 吴亚辉, 周浩浩. 基于分层抽样优化的面向异构客户端的联邦学习 Federated Learning Based on Stratified Sampling Optimization for Heterogeneous Clients 计算机科学, 2022, 49(9): 183-193. https://doi.org/10.11896/jsjkx.220500263
[4]	刘鑫, 王珺, 宋巧凤, 刘家豪. 一种基于AAE的协同多播主动缓存方案 Collaborative Multicast Proactive Caching Scheme Based on AAE 计算机科学, 2022, 49(9): 260-267. https://doi.org/10.11896/jsjkx.210800019
[5]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[6]	姜洋洋, 宋丽华, 邢长友, 张国敏, 曾庆伟. 蜜罐博弈中信念驱动的攻防策略优化机制 Belief Driven Attack and Defense Policy Optimization Mechanism in Honeypot Game 计算机科学, 2022, 49(9): 333-339. https://doi.org/10.11896/jsjkx.220400011
[7]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[8]	袁唯淋, 罗俊仁, 陆丽娜, 陈佳星, 张万鹏, 陈璟. 智能博弈对抗方法:博弈论与强化学习综合视角对比分析 Methods in Adversarial Intelligent Game:A Holistic Comparative Analysis from Perspective of Game Theory and Reinforcement Learning 计算机科学, 2022, 49(8): 191-204. https://doi.org/10.11896/jsjkx.220200174
[9]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[10]	戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105
[11]	陈明鑫, 张钧波, 李天瑞. 联邦学习攻防研究综述 Survey on Attacks and Defenses in Federated Learning 计算机科学, 2022, 49(7): 310-323. https://doi.org/10.11896/jsjkx.211000079
[12]	吴子斌, 闫巧. 基于动量的映射式梯度下降算法 Projected Gradient Descent Algorithm with Momentum 计算机科学, 2022, 49(6A): 178-183. https://doi.org/10.11896/jsjkx.210500039
[13]	徐国宁, 陈奕芃, 陈一鸣, 陈晋音, 温浩. 基于约束优化生成式对抗网络的数据去偏方法 Data Debiasing Method Based on Constrained Optimized Generative Adversarial Networks 计算机科学, 2022, 49(6A): 184-190. https://doi.org/10.11896/jsjkx.210400234
[14]	鲁晨阳, 邓苏, 马武彬, 吴亚辉, 周浩浩. 基于DBSCAN聚类的集群联邦学习方法 Clustered Federated Learning Methods Based on DBSCAN Clustering 计算机科学, 2022, 49(6A): 232-237. https://doi.org/10.11896/jsjkx.211100059
[15]	闫萌, 林英, 聂志深, 曹一凡, 皮欢, 张兰. 一种提高联邦学习模型鲁棒性的训练方法 Training Method to Improve Robustness of Federated Learning 计算机科学, 2022, 49(6A): 496-501. https://doi.org/10.11896/jsjkx.210400298

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed