Task Force on "Transfer Learning & Transfer Optimization"

Task Force Members

Ke Tang, University of Science and Technology of China, ketang@ustc.edu.cn
Kay Chen Tan, City University of Hong Kong, kaytan@cityu.edu.hk
Yaochu Jin, University of Surrey, UK, yaochu.jin@surrey.ac.uk
Hisao Ishibuchi, Osaka Prefecture University, Japan, hisaoi@cs.osakafu-u.ac.jp
Chuan-Kang Ting, National Chung Cheng University, Taiwan, ckting@cs.ccu.edu.tw
Maoguo Gong, Xidian University, China, gong@ieee.org
Wenyin Gong, China University of Geosciences, Wuhan, China, wygong@cug.edu.cn
Meng-Hiot Lim, Nanyang Technological University, Singapore, EMHLIM@ntu.edu.sg
Chaoli Sun, University of Surrey, UK, c.sun@surrey.ac.uk
Huajin Tang, Sichuan University, China, htang@scu.edu.cn
Bo Liu, Chinese Academy of Sciences, China, liub01@mails.tsinghua.edu.cn
Abhishek Gupta, School of Computer Science and Engineering, Nanyang Technological University, Singapore, abhishekg@ntu.edu.sg
Ferrante Neri, De Montfort University, UK, fneri@dmu.ac.uk
Zexuan Zhu, Shenzhen University, China, zhuzx@szu.edu.cn
Brijesh Verma, Central Queensland University, Australia, b.verma@cqu.edu.au
Stefano Cagnoni, University of Parma, Italy, cagnoni@CE.UniPR.IT
Andy Song, RMIT University, Australia, andy.song@rmit.edu.au
Peter Andreae, Victoria University of Wellington, New Zealand, peter.andreae@ecs.vuw.ac.nz
Lin Shang, Nanjing University, China, shanglin@nju.edu.cn
Wenlong Fu, SAP-NZ, New Zealand, wenlong.fu@gmail.com
Harith Al-Sahaf, Victoria University of Wellington, New Zealand, harith.al-sahaf@ecs.vuw.ac.nz
Muhammad Iqbal, Victoria University of Wellington, New Zealand, iqbal_227@hotmail.com
Urvesh Bhowan, Trinity College Dublin, Ireland, urveshb@gmail.com
Ahmed Kattan, Deputy Minister of Labour, Kingdom of Saudi Arabia, kattan.ahmed@gmail.com
Qi Chen, Victoria University of Wellington, New Zealand, Qi.Chen@ecs.vuw.ac.nz
Tribeni Prasad Banerjee, Dr. B.C. Roy Engineering College, Durgapur, West Bengal, India, tribeniju@gmail.com
Yaqing Hou, Dalian University of Technology, China, houyq@dlut.edu.cn
Amiram Moshaiov, Tel-Aviv University, Israel, moshaiov@post.tau.ac.il
Mazhar Ansari Ardeh, School of Engineering and Computer Science, Victoria University of Wellington, New Zealand, mazhar.ansariardeh@ecs.vuw.ac.nz

Motivation

Today, it is well recognized that the processes of learning, and the transfer of what has been learned, are central to humans in problem-solving. Learning has been established to be fundamental to humans in functioning and adapting to our fast evolving society and built surroundings. Besides learning from the successes and mistakes of the past, and accordingly avoiding the same mistakes again, the ability of humans to seamlessly select and generalize relevant experiences to new problems is deemed to be most remarkable.

Within the context of computational intelligence, several core learning technologies in neural and cognitive systems, fuzzy systems, probabilistic and possibilistic reasoning, have shown promise in emulating the generalization capabilities of human learning, with many now used routinely to enhance our daily lives. Recently, in contrast to traditional machine learning approaches, Transfer Learning, which uses data from related source tasks to augment learning in a new (target) task, has attracted extensive attention and demonstrated great success in a wide range of real-world applications, including computer vision, natural language processing, speech recognition, etc.

In spite of several advances in computational intelligence, it is noted that the attempts to emulate such cognitive capabilities in problem solvers, especially those of an evolutionary nature, have received far less attention. In fact, most existing evolutionary algorithms (EAs) remain ill-equipped to exploit the potentially rich sources of knowledge that may be embedded in previous searches. With this, and the observation that any practically useful industrial system is likely to face a large number of (possibly repetitive) problems over a lifetime, it is contended that novel research advances in both the theory and application of Transfer Learning, especially for Optimization, are primed to bring about a new wave in the real-world impact of intelligent systems. The current task force thus presents an attempt to achieve this goal.

Goals

The main goal of this task force is to promote the research on crafting novel algorithm designs as well as theoretical analysis towards "intelligent" evolutionary computation, which possesses the transfer capabilities that evolve along with the problems solved. Further, this task force also aims at providing a forum for academic and industrial researchers to explore future directions of research and promote evolutionary computation techniques to a wider audience in the society of computer science and engineering.

Scope

The scope of this task force includes the following topics:

• Single/Multi-Objective evolutionary algorithms with transfer capability for continuous or combinatorial optimization.
• Theoretical studies that enhance our understandings on the behaviors of evolutionary transfer learning and optimization.
• Transfer learning and data mining in evolutionary computation.
• Evolutionary transfer learning and optimization using big data and data analytics.
• Evolutionary transfer learning and optimization for dynamic optimization problems.
• Real world applications including expensive and complex optimization.
• Evolutionary transfer learning, domain adaptation and domain generalization.
• Hybridization of evolutionary computation and neural networks, and fuzzy systems for transfer learning and optimization.
• Hybridization of evolutionary computation and machine learning, information theory, statistics, etc., for transfer learning.
• Real-world applications, e.g. expensive and complex optimization, text mining, computer vision, image analysis, face recognition, WiFi localization, etc.

Current Activities

• Special Session on Evolutionary Transfer Learning and Transfer Optimisation at IEEE CEC 2021. Click here.
• Competition on Evolutionary Multi-task Optimization at IEEE CEC 2021. Click here.
• IEEE CIM Special Issue on Knowledge Transfer in Evolutionary Optimization. Click here.