2020 International Workshop on
Knowledge Transfer in
Evolutionary Optimization
19 December, 2020, Chongqing, China
Aims and Scope
Evolutionary Algorithms (EAs) are nature-inspired population-based search methods which
work on Darwinian principles of natural selection. Due to their strong search capability and
simplicity of implementation, EAs have been successfully applied to solve many complex
optimization problems, which cannot be easily solved by traditional mathematical programming
approaches, such as linear programming, quadratic programming, and convex optimization.
Despite the great success enjoyed by EAs, it is worth noting that existing EA solvers usually conduct the search process from scratch, regardless how similar the new problem encountered is to those already solved in the past. Therefore, conventional EAs do not learn from previous problems and the search capabilities of the EA solvers do not automatically grow with problem-solving experiences. However, in reality, problems seldom exist in isolation, solving one problem may thus yield useful information for solving other related problems. In the literature, there is a growing interest in conducting research on evolutionary transfer optimization (ETO) in recent years: a paradigm that integrates EA solvers with knowledge learning and transfer across related domains to achieve better optimization efficiency and performance.
Being one of the emerging research areas in computational intelligence, there are many challenges and open research questions in ETO. This workshop aims at introducing and discussing the elementary concepts, the state-of-the-art techniques, as well as the future work directions of ETO.
Through this workshop, we will meet multiple targets which include:
Despite the great success enjoyed by EAs, it is worth noting that existing EA solvers usually conduct the search process from scratch, regardless how similar the new problem encountered is to those already solved in the past. Therefore, conventional EAs do not learn from previous problems and the search capabilities of the EA solvers do not automatically grow with problem-solving experiences. However, in reality, problems seldom exist in isolation, solving one problem may thus yield useful information for solving other related problems. In the literature, there is a growing interest in conducting research on evolutionary transfer optimization (ETO) in recent years: a paradigm that integrates EA solvers with knowledge learning and transfer across related domains to achieve better optimization efficiency and performance.
Being one of the emerging research areas in computational intelligence, there are many challenges and open research questions in ETO. This workshop aims at introducing and discussing the elementary concepts, the state-of-the-art techniques, as well as the future work directions of ETO.
Through this workshop, we will meet multiple targets which include:
-
(1) promoting the research on ETO frameworks and algorithms towards more efficient and effective evolutionary optimization,
-
(2) serving existing CIS members,
-
(3) promoting CIS and attracting new members,
-
(4) attracting industry participants.
Venue and Dates
- Address: Chongqing, China
- Dates: 19 December, 2020
- Time: 2020/12/19 09:00-17:00
- Tencent Meeting ID: 431 212 508
Invited Speakers (list in alphabetical order)
Talk: Data-Driven Evolutionary Computation
Talk: Evolutionary Multitask Optimization
Talk: Many Facets of Learning to Optimise
Talk: Evolutionary Transfer Learning for Image Analysis and Pattern Recognition
Talk: Use of problem relationship in design of heuristics
Program
Program Schedule
09:00 – 09:10
Welcome Address
Prof. Xiaofeng Liao, Chongqing University
09:10 – 09:30
Workshop Opening
Prof. Kay Chen Tan, Hong Kong Polytechnic University
09:30 – 10:15
Keynote 1: Many Facets of Learning to Optimise
Prof. Xin Yao, Southern University of Science and Technology
10:15 – 11:00
Keynote 2: Evolutionary Multitask Optimization
Prof. Yew-Soon Ong, Nanyang Technological University
11:00 – 11:45
Keynote 3: Evolutionary Transfer Learning for Image Analysis and Pattern Recognition
Prof. Mengjie Zhang, Victoria University of Wellington
11:45 – 12:15
Tutorial 1: Explicit Evolutionary Multitasking for Combinatorial Optimization: A Case Study on Capacitated Vehicle Routing Problem
Prof. Liang Feng, Chongqing University
12:15 – 14:00
Lunch Break
14:00 – 14:45
Keynote 4: Use of problem relationship in design of heuristics
Prof. Qingfu Zhang, City University of Hong Kong
14:45 – 15:15
Tutorial 2: Dynamic Evolutionary Multiobjective Optimization: A Knowledge Transfer Approach
Prof. Min Jiang, Xiamen University
15:15 – 15:45
Tutorial 3: Evolutionary Computation for Automated Design of Deep Neural Networks
Prof. Bing Xue, Victoria University of Wellington
15:45 – 16:15
Tutorial 4: An Introduction to Surrogate Models in Evolutionary Computation
Prof. Handing Wang, Xidian University, China
16:15 – 17:00
Keynote 5: Data-Driven Evolutionary Computation
Prof. Yaochu Jin, University of Surrey
Organizing Committee
Advisory Chairs:
Prof. Xiaofeng Liao, Chongqing University, China
Prof. Kay Chen Tan,
Hong Kong Polytechnic University
Program Co-Chairs:
Prof. Min Jiang, Xiamen University, China
Prof. Handing Wang, Xidian University, China
Prof. Bing Xue, Victoria University of Wellington, New Zealand
Prof. Liang Feng, Chongqing University, China
Sponsors:
Chongqing University
Supported by IEEE Computational Intelligence Society, Xiamen Chapter.