A fast and elitist multiobjective genetic algorithm: NSGA-II

By Kalyanmoy Deb, Samir Agrawal, Amrit Pratap, T. Meyarivan. 2002

48,475 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Evaluation & Benchmarks

Citations in the corpus

Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search (2021, methodology): “Finally, as a Genetic Algorithm, the NSGA-II (Deb et al., 2002) has been employed, in order to solve a multi objective optimization problem.”
Weight Agnostic Neural Networks (2019, background): “Rather than attempting to balance these criteria with a hand-crafted reward function for each new task, we rank the solutions based on dominance relations [19].”
GreedyNAS: Towards Fast One-Shot NAS With Greedy Supernet (2020, methodology): “For searching with NSGAII [6] algorithm, we set the population size as 50 and the number of generations as 20.”
FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search (2019, methodology): “Here we adopt a searching algorithm from an NSGA-II [10] with a small variation by using Proximal Policy Optimization [39] as the default reinforcing algorithm.”
A Survey on Neural Architecture Search (2019, methodology): “Kim et al. (2017) and Lu et al. (2018) both employ NSGA-II in order to tackle the problem.”
Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search (2019, methodology): “To be specific, the iteration is controlled by NSGA-II [9], which contains four sub-procedures: population initialization, selection, crossover, and mutation.”
Genetic CNN (2017, neutral): “It is commonly used to generate high-quality solutions to optimization and search problems [14][30][2][4] by performing bio-inspired operators such as mutation, crossover and selection.”
Automating Biomedical Data Science Through Tree-Based Pipeline Optimization (2016, methodology): “In future work, we will explore methods such as multi-objective [19] and Pareto optimization [20], where one of the objectives/Pareto fronts can be pipeline generalization performance or pipeline complexity (assuming less-complex pipelines will generalize better).”
Adaptive Service Composition in Flexible Processes (2007, methodology): “In [13], the multiobjective evolutionary approach NSGA-II (Nondominated Sorting Genetic Algorithm; see [17]) is implemented, which identifies a set of Pareto optimal solutions without introducing a ranking among different quality dimensions.”
A Grid-Based Evolutionary Algorithm for Many-Objective Optimization (2013, neutral): “The procedure of the algorithm is similar to most generational EMO algorithms like NSGA-II [11] and SPEA2 [73] Firstly, population P .”