4.7 Review

A Review on Evolutionary Multitask Optimization: Trends and Challenges

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

A Survey on Multi-Task Learning

Yu Zhang et al.

Summary: This paper provides a survey of Multi-Task Learning (MTL) from the perspective of algorithmic modeling, applications, and theoretical analyses. It discusses different MTL algorithms and their characteristics, as well as the combination of MTL with other learning paradigms. The paper also reviews MTL models for large-scale tasks or high-dimensional data, as well as dimensionality reduction and feature hashing. Real-world applications of MTL are examined, and theoretical analyses and future directions are discussed.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2022)

Article Computer Science, Artificial Intelligence

A Continual Learning Survey: Defying Forgetting in Classification Tasks

Matthias De Lange et al.

Summary: This article introduces the application of artificial neural networks in continual learning, focusing on task incremental classification. It proposes a new framework for continually evaluating the stability-plasticity trade-off of the network and performs experimental comparisons of 11 state-of-the-art continual learning methods, evaluating their strengths and weaknesses by considering different benchmark datasets.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Article Computer Science, Artificial Intelligence

Multi-Task Learning for Dense Prediction Tasks: A Survey

Simon Vandenhende et al.

Summary: With the advent of deep learning, dense prediction tasks have significantly improved. Recent multi-task learning techniques have shown promising results by jointly tackling multiple tasks. This survey provides a comprehensive view on state-of-the-art deep learning approaches for multi-task learning in computer vision, with a focus on dense prediction tasks.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Article Computer Science, Artificial Intelligence

Towards Generalized Resource Allocation on Evolutionary Multitasking for Multi-Objective Optimization

Tingyang Wei et al.

Summary: Researchers have proposed a Generalized Resource Allocation (GRA) framework to dynamically allocate computational resources, enhancing the performance of multi-objective EMTO algorithms. By designing a normalized attainment function, multi-step nonlinear regression, and flexible adjustment of resource allocation intensity, the framework has shown success in various domains.

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE (2021)

Article Computer Science, Information Systems

Multifactorial evolutionary optimization to maximize lifetime of wireless sensor network

Nguyen Thi Tam et al.

Summary: This paper addresses the issue of relay node assignment in wireless single-hop and multi-hop sensor networks in three-dimensional terrains. A multifactorial evolutionary algorithm, MFRSEA, is proposed to optimize for both types of networks simultaneously. Experimental results demonstrate that the method outperforms the baseline in key metrics.

INFORMATION SCIENCES (2021)

Article Computer Science, Artificial Intelligence

Evolutionary Transfer Optimization-A New Frontier in Evolutionary Computation Research

Kay Chen Tan et al.

Summary: Evolutionary Algorithm (EA) is a nature-inspired search method that works on Darwinian principles and has been successfully applied to solve complex optimization problems. Recently, there has been growing interest in Evolutionary Transfer Optimization (ETO) which integrates knowledge learning and transfer across domains to achieve better optimization efficiency and performance. This emerging research field shows promise for developing more advanced ETO methods and applications.

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE (2021)

Article Computer Science, Artificial Intelligence

A Unified Framework of Graph-Based Evolutionary Multitasking Hyper-Heuristic

Xingxing Hao et al.

Summary: Hyper-heuristics and evolutionary multitasking share similarities in search methods, and by combining the advantages of both, the optimization of problems can be accelerated, leading to increased generality.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

Article Computer Science, Artificial Intelligence

Knee Point-Based Imbalanced Transfer Learning for Dynamic Multiobjective Optimization

Min Jiang et al.

Summary: In the dynamic multiobjective optimization problems, utilizing the knee point transfer learning method KT-DMOEA can greatly improve computational efficiency and solution quality.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

Article Computer Science, Artificial Intelligence

Non-linear Domain Adaptation in Transfer Evolutionary Optimization

Ray Lim et al.

Summary: This paper presents a new perspective on domain adaptation in evolutionary optimization, inducing positive transfers even in scenarios of source-target domain mismatch. By establishing a probabilistic formulation and proposing a domain adaptive transfer evolutionary algorithm, it is significant for solving complex problems.

COGNITIVE COMPUTATION (2021)

Article Automation & Control Systems

Ant Colony Evacuation Planner: An Ant Colony System With Incremental Flow Assignment for Multipath Crowd Evacuation

Zhi-Min Huang et al.

Summary: The article proposes an ant colony evacuation planner (ACEP) with a novel solution construction strategy and an incremental flow assignment (IFA) method to address the evacuation path optimization problem. By using the entire colony of ants to find multiple evacuation paths cooperatively, and introducing the IFA method to improve efficiency, the ACEP shows promising results in numerical experiments.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Computer Science, Information Systems

Surrogate-Assisted Evolutionary Framework with Adaptive Knowledge Transfer for Multi-Task Optimization

Shijia Huang et al.

Summary: The paper introduces an efficient surrogate-assisted multi-task evolutionary framework with adaptive knowledge transfer for multi-task optimization, where computationally expensive tasks are solved jointly in each generation, surrogate models are built based on historical search information, and mechanisms for similarity measure and adaptive knowledge transfer are proposed to improve search efficiency. Experimental results show that the proposed framework outperforms several state-of-the-art multi-task optimization algorithms.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING (2021)

Article Computer Science, Artificial Intelligence

Regularized Evolutionary Multitask Optimization: Learning to Intertask Transfer in Aligned Subspace

Zedong Tang et al.

Summary: The article presents a novel and computationally efficient intertask information transfer strategy by aligning subspaces. By introducing a learnable alignment matrix, it extracts complementary information among different tasks to enhance the performance of solving complicated problems. This method shows superior performance compared to existing evolutionary multitask optimization algorithms in comprehensive experiments.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

Article Automation & Control Systems

Cognizant Multitasking in Multiobjective Multifactorial Evolution: MO-MFEA-II

Kavitesh Kumar Bali et al.

Summary: Humans are adept at identifying recurrent patterns in diverse situations, while AI systems strive to mimic such cognitive behavior. Evolutionary multitasking is explored as an effective means of solving multiple optimization tasks simultaneously, yet there is a known limitation in the inability to adapt transfer extent in a principled way.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Automation & Control Systems

Toward Adaptive Knowledge Transfer in Multifactorial Evolutionary Computation

Lei Zhou et al.

Summary: A multifactorial evolutionary algorithm (MFEA) is proposed for evolutionary multitasking, optimizing multiple tasks simultaneously with knowledge transfer. The appropriate configuration of crossover is essential for the performance of MFEA.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Computer Science, Artificial Intelligence

A study on multiform multi-objective evolutionary optimization

Liangjie Zhang et al.

Summary: This paper presents a study on multiform multi-objective evolutionary optimization, which aims to construct multiple forms of a given MOP and simultaneously optimize them using evolutionary search to enhance multi-objective optimization performance. Comprehensive empirical studies were conducted to evaluate the proposed multiform paradigm for multi-objective optimization.

MEMETIC COMPUTING (2021)

Review Mathematics

Multi-Task Optimization and Multi-Task Evolutionary Computation in the Past Five Years: A Brief Review

Qingzheng Xu et al.

Summary: Multi-task evolutionary computation (MTEC) is a novel algorithm paradigm that facilitates knowledge transfer, accelerates convergence, and improves solution quality between optimization tasks. Since 2016, there has been a growing number of specialized literature on MTEC, indicating increased research interest. This review covers the basic concepts, implementation methods, application fields, challenges, and future directions of MTEC.

MATHEMATICS (2021)

Article Computer Science, Artificial Intelligence

A Multipopulation Evolutionary Algorithm for Solving Large-Scale Multimodal Multiobjective Optimization Problems

Ye Tian et al.

Summary: The article proposes an evolutionary algorithm for solving large-scale multimodal multiobjective optimization problems, which can effectively handle problems with a large number of decision variables and outperform state-of-the-art methods in neural architecture search.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

Article Computer Science, Artificial Intelligence

SAFE: Scale-Adaptive Fitness Evaluation Method for Expensive Optimization Problems

Sheng-Hao Wu et al.

Summary: The proposed SAFE method is a novel approach to efficiently solve expensive optimization problems by using a set of evaluation methods with different accuracy scales. Experimental results demonstrate that the method achieves better solution quality compared to baseline and state-of-the-art algorithms.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

Article Computer Science, Artificial Intelligence

Surrogate-Assisted Evolutionary Multitask Genetic Programming for Dynamic Flexible Job Shop Scheduling

Fangfang Zhang et al.

Summary: This paper proposes a novel surrogate-assisted evolutionary multitask algorithm via GP to share useful knowledge between different scheduling tasks to improve training efficiency and effectiveness. Phenotypic characterization is used to measure the behaviors of scheduling rules and build a surrogate for each task. The proposed algorithm successfully improves the quality of scheduling heuristics for all scenarios.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

Article Computer Science, Artificial Intelligence

A Computationally Efficient Evolutionary Algorithm for Multiobjective Network Robustness Optimization

Shuai Wang et al.

Summary: The robustness of complex networks is crucial for their stability, and multiobjective robustness optimization is gaining increasing attention. However, challenges remain, including different computational complexities, insufficient network diversity, and high computational costs. By introducing a computationally efficient multiobjective optimization algorithm, a unique feature-based fitness evaluation method, and a surrogate ensemble based on graph embedding information, these challenges have been successfully addressed.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2021)

Article Automation & Control Systems

Solving Generalized Vehicle Routing Problem With Occasional Drivers via Evolutionary Multitasking

Liang Feng et al.

Summary: This article introduces a new vehicle routing problem, VRPHTO, and validates the cost reduction effect of employing occasional drivers through empirical studies. The proposed multitasking evolutionary algorithm, EMA, can simultaneously solve multiple VRPHTOs and achieve enhanced optimization performance through knowledge transfer between tasks.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Automation & Control Systems

A Fast Dynamic Evolutionary Multiobjective Algorithm via Manifold Transfer Learning

Min Jiang et al.

Summary: A new memory-driven manifold transfer learning-based evolutionary algorithm for dynamic multiobjective optimization (MMTL-DMOEA) is proposed in this article. By combining the mechanism of memory to preserve the best individuals from the past with the feature of manifold transfer learning to predict the optimal individuals, the algorithm significantly improves the quality of solutions at the initial stage and reduces the computational cost required in existing methods.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Automation & Control Systems

An Effective Knowledge Transfer Approach for Multiobjective Multitasking Optimization

Jiabin Lin et al.

Summary: Multiobjective multitasking optimization (MTO) is a novel research topic in the field of evolutionary computation, aiming to solve multiple related multiobjective optimization problems simultaneously using evolutionary algorithms. The key lies in the knowledge transfer based on sharing solutions across tasks. This study proposes a new algorithm to address MTO problems and validates its effectiveness through numerical studies on benchmark problems.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Automation & Control Systems

Explicit Evolutionary Multitasking for Combinatorial Optimization: A Case Study on Capacitated Vehicle Routing Problem

Liang Feng et al.

Summary: This article introduces the concept of Evolutionary Multitasking (EMT), discusses the limitations of autoencoding-based EMT algorithm and explores the application of explicit EMT in combinatorial optimization problems. A new algorithm is proposed for solving the vehicle routing problem, and its effectiveness is validated through empirical studies.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Automation & Control Systems

Multifactorial Genetic Programming for Symbolic Regression Problems

Jinghui Zhong et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2020)

Article Computer Science, Artificial Intelligence

Evolutionary multitasking fuzzy cognitive map learning

Fang Shen et al.

KNOWLEDGE-BASED SYSTEMS (2020)

Article Computer Science, Artificial Intelligence

Multifactorial Evolutionary Algorithm With Online Transfer Parameter Estimation: MFEA-II

Kavitesh Kumar Bali et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2020)

Article Computer Science, Artificial Intelligence

Self-Regulated Evolutionary Multitask Optimization

Xiaolong Zheng et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2020)

Article Computer Science, Information Systems

A Multiobjective multifactorial optimization algorithm based on decomposition and dynamic resource allocation strategy

Shuangshuang Yao et al.

INFORMATION SCIENCES (2020)

Article Computer Science, Theory & Methods

Generalizing from a Few Examples: A Survey on Few-shot Learning

Yaqing Wang et al.

ACM COMPUTING SURVEYS (2020)

Article Computer Science, Artificial Intelligence

Paradoxes in Numerical Comparison of Optimization Algorithms

Qunfeng Liu et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2020)

Article Computer Science, Artificial Intelligence

Multitasking Genetic Algorithm (MTGA) for Fuzzy System Optimization

Dongrui Wu et al.

IEEE TRANSACTIONS ON FUZZY SYSTEMS (2020)

Article Computer Science, Artificial Intelligence

Multiobjective Multitasking Optimization Based on Incremental Learning

Jiabin Lin et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2020)

Article Computer Science, Artificial Intelligence

Multi-surrogate multi-tasking optimization of expensive problems

Peng Liao et al.

KNOWLEDGE-BASED SYSTEMS (2020)

Article Computer Science, Artificial Intelligence

An Adaptive Archive-Based Evolutionary Framework for Many-Task Optimization

Yongliang Chen et al.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2020)

Article Computer Science, Artificial Intelligence

Multiproblem Surrogates: Transfer Evolutionary Multiobjective Optimization of Computationally Expensive Problems

Alan Tan Wei Min et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2019)

Article Computer Science, Artificial Intelligence

Generalized Multitasking for Evolutionary Optimization of Expensive Problems

Jinliang Ding et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2019)

Article Computer Science, Artificial Intelligence

Two-Archive Evolutionary Algorithm for Constrained Multiobjective Optimization

Ke Li et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2019)

Article Computer Science, Information Systems

Migration Modeling and Learning Algorithms for Containers in Fog Computing

Zhiqing Tang et al.

IEEE TRANSACTIONS ON SERVICES COMPUTING (2019)

Article Automation & Control Systems

Evolutionary Multitasking via Explicit Autoencoding

Liang Feng et al.

IEEE TRANSACTIONS ON CYBERNETICS (2019)

Article Computer Science, Artificial Intelligence

A Survey on Cooperative Co-Evolutionary Algorithms

Xiaoliang Ma et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2019)

Article Automation & Control Systems

Curbing Negative Influences Online for Seamless Transfer Evolutionary Optimization

Bingshui Da et al.

IEEE TRANSACTIONS ON CYBERNETICS (2019)

Review Computer Science, Artificial Intelligence

Constrained multi-objective optimization algorithms: Review and comparison with application in reinforced concrete structures

Hamid Afshari et al.

APPLIED SOFT COMPUTING (2019)

Article Computer Science, Artificial Intelligence

Evolutionary Multitasking Sparse Reconstruction: Framework and Case Study

Hao Li et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2019)

Article Computer Science, Artificial Intelligence

Evolutionary Multitasking With Dynamic Resource Allocating Strategy

Maoguo Gong et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2019)

Article Computer Science, Artificial Intelligence

Handling Constrained Multiobjective Optimization Problems With Constraints in Both the Decision and Objective Spaces

Zhi-Zhong Liu et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2019)

Article Computer Science, Artificial Intelligence

A hybrid of genetic transform and hyper-rectangle search strategies for evolutionary multi-tasking

Zhengping Liang et al.

EXPERT SYSTEMS WITH APPLICATIONS (2019)

Article Computer Science, Artificial Intelligence

Rigorous Analysis of Multi-Factorial Evolutionary Algorithm as Multi-Population Evolution Model

Na Wang et al.

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS (2019)

Proceedings Paper Engineering, Electrical & Electronic

Multifactorial optimization using Artificial Bee Colony and its application to Car Structure Design Optimization

Gen Yokoya et al.

2019 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (2019)

Proceedings Paper Engineering, Electrical & Electronic

Multifactorial Differential Evolution with Opposition-based Learning for Multi-tasking Optimization

Yanan Yu et al.

2019 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (2019)

Proceedings Paper Engineering, Electrical & Electronic

A Co-evolutionary Cartesian Genetic Programming with Adaptive Knowledge Transfer

Jinghui Zhong et al.

2019 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (2019)

Proceedings Paper Engineering, Electrical & Electronic

Towards Effective Mutation for Knowledge Transfer in Multifactorial Differential Evolution

Lei Zhou et al.

2019 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (2019)

Proceedings Paper Engineering, Electrical & Electronic

A Preliminary Study of Adaptive Task Selection in Explicit Evolutionary Many-Tasking

Q. Shang et al.

2019 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (2019)

Proceedings Paper Engineering, Electrical & Electronic

A multi-objective multi-factorial evolutionary algorithm with reference-point-based approach

Huynh Thi Thanh Binh et al.

2019 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (2019)

Article Computer Science, Artificial Intelligence

Insights on Transfer Optimization: Because Experience is the Best Teacher

Abhishek Gupta et al.

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2018)

Proceedings Paper Computer Science, Artificial Intelligence

A Guided Differential Evolutionary Multi-tasking with Powell search method for solving Multi-objective Continuous Optimization

Nguyen Quoc Tuan et al.

2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (2018)

Proceedings Paper Computer Science, Artificial Intelligence

A Fast Memetic Multi-objective Differential Evolution for Multi-tasking Optimization

Yongliang Chen et al.

2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (2018)

Proceedings Paper Computer Science, Artificial Intelligence

Surrogate-assisted Multi-tasking Memetic Algorithm

Dingnan Liu et al.

2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC) (2018)

Article Automation & Control Systems

Coevolutionary multitasking for concurrent global optimization: With case studies in complex engineering design

Mei-Ying Cheng et al.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2017)

Article Computer Science, Artificial Intelligence

Cross-Domain Reuse of Extracted Knowledge in Genetic Programming for Image Classification

Muhammad Iqbal et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2017)

Article Automation & Control Systems

Multiobjective Multifactorial Optimization in Evolutionary Multitasking

Abhishek Gupta et al.

IEEE TRANSACTIONS ON CYBERNETICS (2017)

Article Computer Science, Artificial Intelligence

Multifactorial Evolution: Toward Evolutionary Multitasking

Abhishek Gupta et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2016)

Article Computer Science, Artificial Intelligence

Evolutionary Multitasking: A Computer Science View of Cognitive Multitasking

Yew-Soon Ong et al.

COGNITIVE COMPUTATION (2016)

Article Computer Science, Artificial Intelligence

Parameter Control in Evolutionary Algorithms: Trends and Challenges

Giorgos Karafotias et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2015)

Article Computer Science, Artificial Intelligence

Evolutionary multitasking in bi-level optimization

Abhishek Gupta et al.

COMPLEX & INTELLIGENT SYSTEMS (2015)

Proceedings Paper Computer Science, Artificial Intelligence

Unsupervised Visual Domain Adaptation Using Subspace Alignment

Basura Fernando et al.

2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2013)

Article Computer Science, Artificial Intelligence

Evolutionary dynamic optimization: A survey of the state of the art

Trung Thanh Nguyen et al.

SWARM AND EVOLUTIONARY COMPUTATION (2012)

Article Computer Science, Artificial Intelligence

Generalizing Surrogate-Assisted Evolutionary Computation

Dudy Lim et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2010)

Article Computer Science, Artificial Intelligence

A Survey on Transfer Learning

Sinno Jialin Pan et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2010)

Article Computer Science, Artificial Intelligence

A theory of learning from different domains

Shai Ben-David et al.

MACHINE LEARNING (2010)

Article Computer Science, Artificial Intelligence

Opposition versus randomness in soft computing techniques

Shahryar Rahnamayan et al.

APPLIED SOFT COMPUTING (2008)

Article Computer Science, Artificial Intelligence

MOEA/D: A multiobjective evolutionary algorithm based on decomposition

Qingfu Zhang et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2007)

Article Computer Science, Artificial Intelligence

A fast and elitist multiobjective genetic algorithm: NSGA-II

K Deb et al.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2002)