Borg: An Auto-Adaptive Many-Objective Evolutionary Computing Framework

By David Hadka, Patrick M. Reed. Evolutionary Computation, 2013

668 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/2dfb84e0f9bdb3967500e73dd063056eeb7233ed

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

Citations in the corpus

An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point Based Nondominated Sorting Approach, Part II: Handling Constraints and Extending to an Adaptive Approach (2014, methodology): “Although a few many-objective evolutionary algorithms have been suggested in the past [6], [7], [8], [9], [10], [11], [12], there is still a need for more efficient algorithms for many-objective optimization, similar to popular two or three-objective EMO methods, such as NSGA-II [13], SPEA2 [14]…”
A Knee Point-Driven Evolutionary Algorithm for Many-Objective Optimization (2015, background): “This type of ideas has been widely adopted for solving MaOPs, such as ǫ-dominance [22], [23], L-optimality [24], fuzzy dominance [25], and preference order ranking [26].”
Evolutionary algorithms and other metaheuristics in water resources: Current status, research challenges and future directions (2014, methodology): “to a number of signals during the run: (i) time-variant, where the parameter changes according to the length of time the optimisation has been running; (ii) progress-variant, where the parameter is tuned according to the level of success attained by the algorithm and (iii) operator-improvement-varia”
An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point-Based Nondominated Sorting Approach, Part I: Solving Problems With Box Constraints (2014, methodology): “Hadka and Reed [42] suggested an ensemble-based EMO procedure that uses a suitable recombination operator adaptively chosen from a set of eight to ten different predefined operators based on their generation-wise success rate in a problem.”
A survey on multi-objective evolutionary algorithms for many-objective problems (2014, background): “In that work, authors considered 33 instances of 18 unconstrained real valued test problems to compare the NSGA-II [24], the SPEA2 [110], the -MOEA [67], the -NSGA-II [59], a version of the MOEA/D [105], the IBEA [106], the differential evolution method introduced in [65] (GDE3), the Multi-Objective”
Bio-inspired computation: Where we stand and what's next (2019, background): “This is the basic idea of Borg [125], which adopts 𝜖-dominance, a measure of convergence speed called 𝜖 progress, an adaptive population size, multiple recombination operators and a steady-state selection mechanism.”
Test Problems for Large-Scale Multiobjective and Many-Objective Optimization (2017, methodology): “As recommended by Hadka and Reed [67], the Borg framework can be promising in the design of such new MOEAs, where auto-adaptive techniques is adopted to address some of the above issues, e.g., different selection and reproduction operators can be applied to the search of different ﬁtness landscapes.”
A Reference Vector Guided Evolutionary Algorithm for Many-Objective Optimization (2016, background): “Examples of modified dominance definitions includeǫ-dominance [17], [18],L-optimality [19], preference order ranking [20] and fuzzy dominance [21].”
A Decision Variable Clustering-Based Evolutionary Algorithm for Large-Scale Many-Objective Optimization (2018, background): “To enhance the convergence pressure, the most intuitive idea is to directly modify the definition of traditional Pareto dominance, such as ε-dominance [12], [13], L-optimality [14], fuzzy dominance [15], preference order ranking [16], and θ -dominance [17].”