IEEE Transactions on Evolutionary Computation最新文献_第5页

IEEE Computational Intelligence Society Information IEEE计算智能学会信息

IF 15.9 1区计算机科学

IEEE Transactions on Evolutionary Computation Pub Date : 2026-10-01 Epub Date: 2026-10-02 DOI: 10.1109/TEVC.2026.3730928

引用次数: 0

Efficient Evolutionary Neural Architecture Search With Hierarchical Parameter Mapping for Monocular Depth Estimation 基于分层参数映射的高效进化神经结构搜索单目深度估计

IF 15.9 1区计算机科学

IEEE Transactions on Evolutionary Computation Pub Date : 2026-10-01 Epub Date: 2025-09-24 DOI: 10.1109/TEVC.2025.3614261

Haoyu Zhang;Zhihao Yu;Yaochu Jin;Xiufeng Liu;Weiguo Sheng;Ruyu Liu;Xiumei Li;Qiqi Liu;Ran Cheng

{"title":"Efficient Evolutionary Neural Architecture Search With Hierarchical Parameter Mapping for Monocular Depth Estimation","authors":"Haoyu Zhang;Zhihao Yu;Yaochu Jin;Xiufeng Liu;Weiguo Sheng;Ruyu Liu;Xiumei Li;Qiqi Liu;Ran Cheng","doi":"10.1109/TEVC.2025.3614261","DOIUrl":"10.1109/TEVC.2025.3614261","url":null,"abstract":"monocular depth estimation (MDE) plays a crucial role in various real-world applications, including autonomous driving and augmented reality. However, automating the design of efficient MDE models via neural architecture search (NAS) remains challenging due to the high computational cost associated with: 1) pretraining numerous candidate encoders on large-scale datasets such as ImageNet and 2) the substantial memory demands of high-resolution depth estimation models. To address these issues, this article introduces PTF-EvoMDE, an evolutionary NAS framework that eliminates the need for per-candidate pretraining. PTF-EvoMDE incorporates a hierarchical parameter mapping (HPM) strategy that transfers weights from a single pretrained template network (MobileNetV2) to candidate architectures with varying depths, widths, and kernel sizes, significantly reducing computational overhead. Additionally, a feature-aligned conditional random fields (Fa-CRFs) decoder is proposed, leveraging deformable convolutions to dynamically align features and mitigate spatial misalignment, thereby enhancing depth prediction accuracy. Experiments on the KITTI benchmark demonstrate that PTF-EvoMDE achieves an absolute relative error (Abs Rel) of 0.061 and a root mean squared error (RMSE) of 2.470, comparable to dense prediction transformer (DPT) model (Abs Rel: 0.062, RMSE: 2.573) while requiring only 5% of the parameters. Moreover, PTF-EvoMDE reduces the computational cost of NAS by more than 75% compared to conventional evolutionary approaches that rely on per-candidate pretraining. The resulting lightweight encoder exhibits strong transferability, achieving competitive performance on COCO object detection (42.1% mean average precision (mAP)) and Cityscapes semantic segmentation (76.4% mean intersection-over-union (mIoU)) with minimal fine-tuning.","PeriodicalId":13206,"journal":{"name":"IEEE Transactions on Evolutionary Computation","volume":"30 5","pages":"1893-1907"},"PeriodicalIF":15.9,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145133619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evolving Generalizable Parallel Algorithm Portfolios for Binary Optimization Problems via Domain-Agnostic Instance Generation 基于领域不可知实例生成的二元优化问题演化可推广并行算法组合

IF 15.9 1区计算机科学

IEEE Transactions on Evolutionary Computation Pub Date : 2026-10-01 Epub Date: 2025-11-19 DOI: 10.1109/TEVC.2025.3635185

Zhiyuan Wang;Shengcai Liu;Peng Yang;Ke Tang

{"title":"Evolving Generalizable Parallel Algorithm Portfolios for Binary Optimization Problems via Domain-Agnostic Instance Generation","authors":"Zhiyuan Wang;Shengcai Liu;Peng Yang;Ke Tang","doi":"10.1109/TEVC.2025.3635185","DOIUrl":"10.1109/TEVC.2025.3635185","url":null,"abstract":"Generalization is the core objective when training optimizers from data. However, limited training instances often constrain the generalization capability of the trained optimizers. Co-evolutionary approaches address this challenge by simultaneously evolving a parallel algorithm portfolio (PAP) and an instance population to eventually obtain PAPs with good generalization. Yet, when applied to a specific problem class, these approaches have a major limitation. They require practitioners to provide instance generators specially tailored to the problem class, which is often nontrivial to design. This work proposes a general-purpose, off-the-shelf PAP construction approach, named domain-agnostic co-evolution of parameterized search (DACE), for binary optimization problems where decision variables take values of 0 or 1. The key novelty of DACE lies in its neural network-based domain-agnostic instance representation and generation mechanism that eliminates the need for domain-specific instance generators. The strong generality of DACE is validated across three real-world binary optimization problems: 1) the complementary influence maximization problem (CIMP); 2) the compiler arguments optimization problem (CAOP); and 3) the contamination control problem (CCP). Given only a small set of training instances from these problem classes, DACE, without requiring domain knowledge, constructs PAPs with even better generalization performance than existing approaches on all three classes, despite their use of domain-specific instance generators.","PeriodicalId":13206,"journal":{"name":"IEEE Transactions on Evolutionary Computation","volume":"30 5","pages":"2093-2107"},"PeriodicalIF":15.9,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145553454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Deep Reinforcement Learning Framework Assisted by Genetic Programming for Dynamic Flexible Job Shop Scheduling 动态柔性作业车间调度的遗传规划辅助深度强化学习框架

IF 15.9 1区计算机科学

IEEE Transactions on Evolutionary Computation Pub Date : 2026-10-01 Epub Date: 2025-12-29 DOI: 10.1109/TEVC.2025.3649289

Fuqing Zhao;Cheng Zhao;Ling Wang;Hongyan Sang

{"title":"A Deep Reinforcement Learning Framework Assisted by Genetic Programming for Dynamic Flexible Job Shop Scheduling","authors":"Fuqing Zhao;Cheng Zhao;Ling Wang;Hongyan Sang","doi":"10.1109/TEVC.2025.3649289","DOIUrl":"https://doi.org/10.1109/TEVC.2025.3649289","url":null,"abstract":"The dynamic flexible job shop scheduling problem with jobs arriving (DFJSP-JA) is a critical scheduling problem in electrolytic aluminum production processes within the aluminum industry. In the DFJSP-JA, job processing information is obtained after job arrival, thus requiring real-time decisions to minimize total tardiness (TTD). A tree-structured long short-term memory deep reinforcement learning framework with behavior clustering-based multitree genetic programming (TDRL-BCMTGP) is proposed to address the DFJSP-JA. Behavior clustering is introduced to group the candidates of the multitree genetic programming (MTGP) to expedite the iterative generation of high-quality scheduling rules by improving the population diversity of the MTGP. A tree-structured long short-term memory (Tree-LSTM) model trained via contrastive learning generates embedding vectors that capture the structural discrepancy and semantic similarity of the candidates. The embedding vectors are concatenated with the shop floor states and fed into the policy network to train an effective agent. Experimental results demonstrate that the TDRL-BCMTGP framework outperforms state-of-the-art methods in minimizing the TTD across four types of dynamic shop floor scenarios in electrolytic aluminum production processes, while maintaining robust generalization capability under simulated time delays and dynamic changes in shop floor machines.","PeriodicalId":13206,"journal":{"name":"IEEE Transactions on Evolutionary Computation","volume":"30 5","pages":"2138-2151"},"PeriodicalIF":15.9,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Runtime Analysis of Evolutionary Algorithms for Multiparty Multiobjective Optimization 多方多目标优化进化算法的运行时分析

IF 15.9 1区计算机科学

IEEE Transactions on Evolutionary Computation Pub Date : 2026-10-01 Epub Date: 2025-11-05 DOI: 10.1109/TEVC.2025.3629419

Yuetong Sun;Peilan Xu;Wenjian Luo

{"title":"Runtime Analysis of Evolutionary Algorithms for Multiparty Multiobjective Optimization","authors":"Yuetong Sun;Peilan Xu;Wenjian Luo","doi":"10.1109/TEVC.2025.3629419","DOIUrl":"10.1109/TEVC.2025.3629419","url":null,"abstract":"In scenarios where multiple decision-makers operate within a common decision space, each focusing on their own multiobjective optimization problem (e.g., bargaining games), the problem can be modeled as a multiparty MOP (MPMOP). While numerous evolutionary algorithms have been proposed to solve MPMOPs, most results remain empirical. This article presents the first theoretical analysis of the expected runtime of evolutionary algorithms on bi-party MOPs (BPMOPs). Our findings demonstrate that employing traditional multiobjective optimization algorithms to solve MPMOPs is both time-consuming and inefficient, as the resulting population contains many solutions that fail to achieve consensus among decision-makers. An alternative approach involves decision-makers individually solving their respective optimization problems and seeking consensus only in the final stage. While feasible for pseudo-Boolean optimization problems, this method may fail to guarantee approximate performance for one party in NP-hard problems. Finally, we propose evolutionary multiparty multiobjective optimizers (EMPMO) for pseudo-Boolean optimization and shortest path (SP) problems within a multiparty multiobjective context, maintain a common solution set among all parties. Theoretical and experimental results demonstrate that the proposed <inline-formula> <tex-math>$ text {EMPMO}_{text {random}} $ </tex-math></inline-formula> outperforms previous algorithms in terms of the lower bound on the expected runtime for pseudo-Boolean optimization problems. Additionally, the consensus-based evolutionary multiparty multiobjective optimizer(<inline-formula> <tex-math>$ text {EMPMO}_{text {cons}}^{text {SP}} $ </tex-math></inline-formula>) achieves better efficiency and precision in solving SP problems compared to existing algorithms.","PeriodicalId":13206,"journal":{"name":"IEEE Transactions on Evolutionary Computation","volume":"30 5","pages":"2024-2038"},"PeriodicalIF":15.9,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145447359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Weak Pareto Boundary: A Critical Challenge for Evolutionary Multiobjective Optimization 弱Pareto边界：进化多目标优化的一个关键挑战

IF 15.9 1区计算机科学

IEEE Transactions on Evolutionary Computation Pub Date : 2026-10-01 Epub Date: 2025-12-22 DOI: 10.1109/TEVC.2025.3646963

Ruihao Zheng;Jingda Deng;Zhenkun Wang

{"title":"Weak Pareto Boundary: A Critical Challenge for Evolutionary Multiobjective Optimization","authors":"Ruihao Zheng;Jingda Deng;Zhenkun Wang","doi":"10.1109/TEVC.2025.3646963","DOIUrl":"10.1109/TEVC.2025.3646963","url":null,"abstract":"The weak Pareto boundary (WPB) refers to a boundary in the objective space of a multiobjective optimization problem, characterized by weak Pareto optimality rather than Pareto optimality. The WPB brings severe challenges to multiobjective evolutionary algorithms (MOEAs), as it may mislead the algorithms into finding dominance-resistant solutions (DRSs), i.e., solutions that excel on some objectives but severely underperform on the others, thereby missing Pareto-optimal solutions. Although the severe impact of the WPB on MOEAs has been recognized, a systematic and detailed analysis remains lacking. To fill this gap, this article studies the attributes of the WPB. In particular, the category of a WPB, as an attribute derived from its weakly Pareto-optimal property, is theoretically analyzed. The analysis reveals that the dominance resistance degrees of DRSs induced by different categories of WPBs exhibit distinct asymptotic growth rates as the DRSs in the objective space approach the WPBs, where a steeper asymptotic growth rate indicates a greater hindrance to MOEAs. Beyond that, experimental studies are conducted on various new test problems to investigate the impact of WPB’s attributes. The experimental results demonstrate consistency with our theoretical findings. Experiments on other attributes show that the performance of an MOEA is highly sensitive to some attributes. Overall, no existing MOEAs can comprehensively address challenges brought by these attributes.","PeriodicalId":13206,"journal":{"name":"IEEE Transactions on Evolutionary Computation","volume":"30 5","pages":"2215-2229"},"PeriodicalIF":15.9,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145807374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

POGP: Probabilistic Genetic Programming With Knowledge Learning for Few-Shot Image Classification 基于知识学习的基于概率遗传规划的少镜头图像分类

IF 15.9 1区计算机科学

IEEE Transactions on Evolutionary Computation Pub Date : 2026-10-01 Epub Date: 2025-12-11 DOI: 10.1109/TEVC.2025.3642991

Xiaowen Huang;Yang Zhang;Zilu Wang;Le Yang;Hongsong Wang;Leimin Wang

{"title":"POGP: Probabilistic Genetic Programming With Knowledge Learning for Few-Shot Image Classification","authors":"Xiaowen Huang;Yang Zhang;Zilu Wang;Le Yang;Hongsong Wang;Leimin Wang","doi":"10.1109/TEVC.2025.3642991","DOIUrl":"10.1109/TEVC.2025.3642991","url":null,"abstract":"Genetic programming (GP) has achieved promising results without relying on the extraction of prior knowledge, e.g., fixed network architecture. However, most existing GP methods guide the evolutionary process by optimizing only the fitness function. In the few-shot image classification task, this single optimization approach can cause the model to converge prematurely to a local optimum, resulting in overfitting. Recently, knowledge learning-assisted evolutionary algorithms have demonstrated remarkable performance by making full use of evolutionary information to guide the evolutionary process. However, existing methods cannot be directly applied to a GP-based method. To address these limitations, we propose a novel framework called probabilistic GP with knowledge learning (POGP). Specifically, we design the redress-forget mechanism of External Archiving to explore the potential of global information and to reupdate external archives using a validation set, effectively utilizing evolutionary information while maintaining population diversity. Furthermore, the probabilistic initialization strategy is designed to initialize the population using evolutionary information when it falls into a local optimum, aiming to enhance the population’s exploration ability. Moreover, we introduce knowledge learning-guide evo-operations to improve the algorithm’s ability to develop optimal solutions by fusing local and global information to guide the population’s search direction. The experiments on benchmark datasets indicate that POGP outperforms state-of-the-art neural network-based and GP-based methods in almost all comparisons, demonstrating the effectiveness of the proposed POGP framework.","PeriodicalId":13206,"journal":{"name":"IEEE Transactions on Evolutionary Computation","volume":"30 5","pages":"2200-2214"},"PeriodicalIF":15.9,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145728825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Relation Reasoning with LLMs in Expensive Optimization 昂贵优化中llm的关系推理

IF 14.3 1区计算机科学

IEEE Transactions on Evolutionary Computation Pub Date : 2026-09-30 DOI: 10.1109/tevc.2026.3738898

Ye Lu, Bingdong Li, Aimin Zhou, Hao Hao

引用次数: 0

A Budget-Aware Feasibility-Guided Surrogate-Assisted Evolutionary Algorithm for Energy-Aware Distributed Hybrid Flow Shop Scheduling 能量感知分布式混合流水车间调度的预算感知可行性导向代理辅助进化算法

IF 14.3 1区计算机科学

IEEE Transactions on Evolutionary Computation Pub Date : 2026-09-28 DOI: 10.1109/tevc.2026.3737767

Fuqing Zhao, Nijiaer Sun, Ling Wang, Hongyan Sang

引用次数: 0

AutoMOAE: Multi-Objective Auto-Algorithm Evolution AutoMOAE：多目标自动算法进化