Data for EMO2023 Paper "Feature-based Benchmarking of Distance-based Multi/Many-objective Optimisation Problems: A Machine Learning Perspective"
DOI10.5281/zenodo.7155803Zenodo7155803MaRDI QIDQ6699510FDOQ6699510
Dataset published at Zenodo repository.
Sébastien Verel, Richard Allmendinger, Arnaud Liefooghe, Kaisa Miettinen, Jonathan Fieldsend, Tinkle Chugh
Publication date: 20 March 2023
Copyright license: Creative Commons Attribution 4.0 International
Data for Paper Feature-based Benchmarking of Distance-based Multi/Many-objective Optimisation Problems: A Machine Learning Perspective The file dbmopp_dataset_perf.csv contains results from the 945 x 30 instances, with the following columns: design_id: problem identifier n_var: number of variables {2, ..., 20} n_obj: number of objectives {2, ..., 10} nonident_ps: non-identical Pareto sets {0 (no), 1 (yes)} var_density: varying density {0 (no), 1 (yes)} n_discon_ps: number of disconnected Pareto sets {0, ..., 6} n_local_fronts: number of local fronts {0, ..., 6} n_resist_regions: number of dominance resistance regions {0, ..., 6} instance_id: instance (fold) identifier {1, ..., 30} budget: number of evaluations performed by the algorithm {5000, 10000, 30000, 50000} algo: multi-objective evolutionary algorithm {NSGAII, IBEA, MOEAD, Random} hypervolume: hypervolume reached by the algorithm [0.0, 1.0] The file dbmopp_dataset_perf_aggregated.csv contains average results from the 945 problems, with the following columns: design_id: problem identifier n_var: number of variables {2, ..., 20} n_obj: number of objectives {2, ..., 10} nonident_ps: non-identical Pareto sets {0 (no), 1 (yes)} var_density: varying density {0 (no), 1 (yes)} n_discon_ps: number of disconnected Pareto sets {0, ..., 6} n_local_fronts: number of local fronts {0, ..., 6} n_resist_regions: number of dominance resistance regions {0, ..., 6} budget: number of evaluations performed by the algorithm {5000, 10000, 30000, 50000} algo: multi-objective evolutionary algorithm {NSGAII, IBEA, MOEAD, Random} hypervolume_avg: average hypervolume reached by the algorithm [0.0, 1.0] best: 1 if the corresponding algorithm obtains the best average hypervolume, 0 otherwise
This page was built for dataset: Data for EMO2023 Paper "Feature-based Benchmarking of Distance-based Multi/Many-objective Optimisation Problems: A Machine Learning Perspective"
