【学术报告】Knowledge Transfer in Bayesian Evolutionary Optimization of Multi-objective Problems with Heterogeneous Objectives
发布人:赵振华  发布时间:2022-08-26   浏览次数:10

英文版:

题目:Academic Report Notice of Yaochu JinKnowledge Transfer in Bayesian Evolutionary Optimization of Multi-objective Problems with Heterogeneous Objectives

Speaker: Professor  Yaochu Jin


Title: Knowledge Transfer in Bayesian Evolutionary Optimization of Multi-objective Problems with Heterogeneous Objectives

Time: 15:30-16:30, August 27, 2022 (Saturday)

Website: https://meeting.tencent.com/dm/3TDQ0GJ0sJEL Tencent meeting

 (meeting number:963 453 406

Abstract:

    For many real-world multi-objective optimization problems, the computational cost for evaluating different objectives varies from objective to objective. Such problems are known as heterogeneously expensive multi-objective optimization problems. To enhance the performance in optimizing heterogeneous multi-objective problems, this talk presents three algorithms for transferring knowledge from the cheaper objective to the more expensive objective by means of parameter based, instance based and domain-adaptation based transfer learning. Finally, we introduce an approach for many-objective heterogeneous expensive problems by alleviating search bias. Empirical results confirm the effectiveness of the proposed algorithms.

Personal Introduction: 

  Yaochu Jin is an Alexander von Humboldt Professor for Artificial Intelligence endowed by the German Federal Ministry of Education and Research, with the Faculty of Technology, Bielefeld University, Germany. He is also a Surrey Distinguished Chair, Professor in Computational Intelligence, Department of Computer Science, University of Surrey, Guildford, U.K. He was a “Finland Distinguished Professor” of University of Jyväskylä, Finland, “Changjiang Distinguished Visiting Professor”, Northeastern University, China, and “Distinguished Visiting Scholar”, University of Technology Sydney, Australia. His main research interests include evolutionary optimization and learning, trustworthy machine learning and optimization, and evolutionary developmental AI. Prof Jin is presently the Editor-in-Chief of Complex & Intelligent Systems. He was the Editor-in-Chief of the IEEE Transactions on Cognitive and Developmental Systems, an IEEE Distinguished Lecturer in 2013-2015 and 2017-2019, the Vice President for Technical Activities of the IEEE Computational Intelligence Society (2015-2016). He is the recipient of the 2018 and 2021 IEEE Transactions on Evolutionary Computation Outstanding Paper Award, and the 2015, 2017, and 2020 IEEE Computational Intelligence Magazine Outstanding Paper Award. He was named by the Web of Science as “a Highly Cited Researcher” consecutively from 2019 to 2021. He is a Member of Academia Europaea and Fellow of IEEE.

 [Editor:Jian Wang]

中文版:

 

题目:金耀初教授学术报告通知:异构多目标问题贝叶斯进化优化中的知识迁移

内容: 

报 告 人:金耀初教授

工作单位:德国比勒费尔德大学技术学院 

报告题目:异构多目标问题贝叶斯进化优化中的知识迁移

 报告时间2022827日(周六)15:30-16:30

 会议网址https://meeting.tencent.com/dm/3TDQ0GJ0sJEL (腾讯会议)

(会议号:963 453 406

内容摘要:

  对于许多现实世界的多目标优化问题,评估不同目标的计算成本因目标而异,将此类问题称为异构昂贵多目标优化问题。为了提高异构多目标优化问题的性能,本报告提出三种算法,分别是通过基于参数、基于实例和基于域适应的迁移学习,将知识从更廉价的目标转移到更昂贵的目标。最后,将介绍一种通过减缓搜索偏差来解决多目标异构昂贵问题的方法,其实验结果证实了该算法的有效性。

 

个人简介:

  金耀初教授是欧洲科学院院士和 IEEE 会士,目前为德国比勒费尔德大学工程学院“洪堡人工智能教授”,兼任英国萨里大学计算机系“计算智能教授”;曾任芬兰于韦斯屈莱大学“芬兰特聘教授”、中国东北大学“长江特聘客座教授”、澳大利亚悉尼科技大学“杰出访问学者”。主要研究方向为:进化优化学习、可信机器学习与优化、进化发育人工智能。金耀初教授目前担任《Complex & Intelligent Systems》主编,曾任《IEEE Transactions on Cognitive and Developmental Systems》主编,2013-2015年和2017-2019年的IEEE杰出讲师以及IEEE计算智能学会技术活动副主席(2015-2016)。金耀初教授获2018年和2021IEEE Transactions on Evolutionary Computation杰出论文奖及2015年、2017年和2020 IEEE计算智能杂志杰出论文奖,并于2019年至2021年连续入选Web of Science“高被引科学家”名单。目前,金耀初教授当选为IEEE CIS 主席。

【编辑:王健】