Research map / Learning theory and algorithms / Combinatorial and search optimization
Fuzzy-Classification Assisted Solution Preselection in Evolutionary Optimization
Aimin Zhou, Jinyuan Zhang, Jianyong Sun, Guixu Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add fuzzy classification preselection (FCPS) to CoDE | CoDE · YLL f1 | median objective value: 2.02e-67 -> 1.86e-145 | Improved |
| add FCPS to CoDE | CoDE · YLL f5 | median objective value: 5.54e-13 -> 8.69e-06 | Hurt |
| add FCPS to CoDE | CoDE · YLL f9 | median objective value: 0.00e+00 -> 1.99e+00 | Hurt |
| add FCPS to CoDE | CoDE · YLL f13 (and f6, f8, f10-f13) | median objective value | No clear effect |
| add FCPS to EDA/LS | EDA/LS · YLL f1 | median objective value: 3.59e-130 -> 3.09e-153 | Improved |
| add FCPS to EDA/LS | EDA/LS · YLL f3, f5, f6, f8-f13 | median objective value | No clear effect |
| replace binary CART classification with fuzzy KNN classification (ablation) | FCPS-CoDE · YLL f1 | median objective value: 5.69e-104 -> 1.86e-145 | Improved |
| replace binary CART classification with fuzzy KNN classification (ablation) | FCPS-CoDE · YLL f5 | median objective value: 7.83e-24 -> 8.69e-06 | Hurt |
| use Q1S/Q2S/Q3S quantile training-set labeling instead of mean-fitness separation (MS) (ablation) | FCPS-CoDE · YLL f1, f4, f9, f11 | mean f vs FES | Hurt |
| replace fuzzy classifier with Btree surrogate model (ablation) | FCPS-CoDE · YLL f1 | median objective value: 1.20e-107 -> 1.86e-145 | Improved |
| replace fuzzy classifier with Btree surrogate model (ablation) | FCPS-CoDE · YLL f5 | median objective value: 8.69e-06 -> 1.25e-25 | Hurt |
| replace fuzzy classifier with SVM/GP/RBF surrogates (ablation) | FCPS-CoDE · YLL f7 | median objective value: 1.62e-03 -> 1.27e-03 | Mixed |
Closest papers by meaning
- Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint (ICML 2025 · similarity 0.80)
- Towards Running Time Analysis of Interactive Multi-Objective Evolutionary Algorithms (AAAI 2024 · similarity 0.79)
- Speeding Up the NSGA-II with a Simple Tie-Breaking Rule (AAAI 2025 · similarity 0.78)
- A Many-Objective Problem Where Crossover Is Provably Indispensable (AAAI 2025 · similarity 0.77)
- Search Strategy Generation for Branch and Bound Using Genetic Programming (AAAI 2025 · similarity 0.77)
- Learning Configurations for Data-Driven Multi-Objective Optimization (ICML 2025 · similarity 0.77)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
