Jul 2026· Annual Conference on Genetic and Evolutionary Computation· pp. 1285-1294· 0 citations· 72 references
Computer Science
TL;DR
This work introduces Automated Deep-learning-based Particle Swarm Optimization (AD-PSO), a framework that highly automates PSO configuration and execution and features a modular design, incorporating diverse PSO variants as interchangeable components.
Abstract
Particle Swarm Optimization (PSO) is a popular gradient-free meta-heuristic, but its many variants pose significant selection and tuning challenges for non-specialists. We introduce Automated Deep-learning-based Particle Swarm Optimization (AD-PSO), a framework that highly automates PSO configuration and execution. AD-PSO features a modular design, incorporating diverse PSO variants as interchangeable components. The core methodology involves training a hard-constrained Conditional Variational Autoencoder (CVAE) to map problem landscape features—obtained via Latin Hypercube Sampling (LHS)—to a near-optimal PSO configuration. This mapping is established a priori through meta-optimization. The user only specifies the maximum number of evaluations; AD-PSO then autonomously samples the function, computes its features, and uses the trained CVAE to generate and execute a tailored configuration. Experimental results demonstrate AD-PSO's strong adaptability. In 297 comparisons on the CEC2022 benchmark against 9 state-of-the-art competitors, AD-PSO won or tied in 239 cases (an 80.5% win/draw rate).
Comprehensive experiments on numerical benchmarks and neuroevolution robotic control tasks demonstrate that AutoPSO consistently discovers novel PSO variants that significantly outperform strong baselines and confirm that AutoPSO achieves increasing performance gains with larger swarm sizes.
Xin-Meng Yu, Jia-Xin Gao, Jianguo Zhang et al.· IEEE Transactions on Evoluti...· 1 citation
Adaptive Hybrid PSO (AHPSO), which uses a sigmoid function on swarm diversity to automatically modulate gradient influence: near-zero during exploration, near-maximum during exploitation, with no manual phase-switching, is proposed.
Traditional particle swarm optimization (PSO) easily falls into premature convergence, while differential evolution (DE) is highly sensitive to fixed control parameters. Existing PSO-DE hybrid frameworks suffer from static population sizes and insufficient cross-population information exchange. This paper proposes PSO-DE-ADP, a hybrid optimizer with sinusoidal adaptive parameters, elite-guided mutation, ring neighborhood-weighted PSO and fitness-driven dynamic dual-population allocation. Four complementary mechanisms are integrated: (i) sine-wave perturbation superimposed on linear decay adaptively adjusts PSO inertia weight, acceleration factors and DE scaling/crossover coefficients to balance search stages; (ii) global elite individuals are embedded into DE mutation to reduce blind random search; (iii) ring topology with weighted learning realizes bidirectional information interaction between PSO and DE subpopulations; (iv) the proportion of PSO/DE individuals is dynamically adjusted according to elite ratio to allocate computing resources. Experiments adopt the CEC2017 30-dimensional benchmark with 30 test functions covering unimodal, multimodal, hybrid and composite landscapes. Compared with 8 state-of-the-art metaheuristics, PSO-DE-ADP achieves the lowest Friedman rank (1.08 vs. 2.23–4.90 for PSO variants; 1.53 vs. 2.07–5.00 for non-PSO algorithms). Ablation tests prove each component significantly boosts accuracy; The algorithm only costs 0.172 s average runtime, superior to all competitors. Statistical Wilcoxon and Friedman tests verify its significant superiority. Future work extends this method to multi-objective, constrained and real engineering optimization tasks.
Yao-Pei Wang, Yufeng Wang, Ke Liu· Algorithms· 0 citations
This study suggests that RLDMGO can serve as a viable and adaptive solver for complex optimization problems and achieves a competitive ranking among fourteen evaluated state-of-the-art competitors.
