A many-objective evolutionary algorithm based on corner solution and cosine distance

Wang, Mengzhen; Ge, Fangzhen; Chen, Debao; Liu, Huaiyu

doi:10.1007/s10489-022-03883-9

Cited by 4 publications

(2 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the distance metric, this paper uses the cosine distance (M. Wang et al, 2022) to compute the dissimilarity between vectors. Given two solution vectors x and y, their cosine distances are:…”

Section: Mating Selection Strategymentioning

confidence: 99%

A Many-Objective Evolutionary Algorithm Based on Non-Linear Dominance

Zhou

Dai

Xue

2023

International Journal of Swarm Intelligence Research

View full text Add to dashboard Cite

With the increase in the number of objectives, the number of non-dominated solutions will also increase sharply. The sorting method based on the traditional Pareto dominance is not sufficiently distinguishable from the solutions and cannot provide enough selection pressure when the population size is small. In this article, a new non-linear dominance (NLD) method is proposed. The main motivation of this method is from the perspective of storage solutions. The number of solutions is small and the difference between each component is as large as possible, so the part of the first quadrant, the second, and the fourth quadrant near the first quadrant becomes the dominant interval, except for the distance too far also defined as the dominant interval, for which construct a parabolic shape of the non-dominant interval. Based on this relationship, the authors propose a non-linear dominated many-objective evolutionary algorithm (NLDEA), which can solve the irregular Pareto front. Experiments show that NLDEA is competitive with the most advanced methods for various scalable benchmark problems.

show abstract

Section: Mating Selection Strategymentioning

confidence: 99%

A Many-Objective Evolutionary Algorithm Based on Non-Linear Dominance

Zhou

Dai

Xue

2023

International Journal of Swarm Intelligence Research

View full text Add to dashboard Cite

show abstract

“…However, the existing similarity calculations, such as Euclidean distance [2], Manhattan distance [3] and cosine distance [4], all operate on the value of the corresponding attribute, which ignores the importance of each attribute [5]. Because there are redundant attributes in the data and different attributes have different weights.…”

Section: Introductionmentioning

confidence: 99%

Piecewise Weighting Function for Collaborative Filtering Recommendation

Zhang¹,

Li²

2022

Preprint

View full text Add to dashboard Cite

<p>It is not always reasonable to set a fixed weight value to an attribute (or a variable) because this cannot accurately maintain the similarity between users and leads to decrease the performance of collaborative filtering recommendation algorithms. In this paper, a piecewise weighting method is proposed with the hyper-class representation for improving the collaborative filtering recommendation. Specifically, a kernel function is first applied to map the original data into the kernel space, and to learn the weight of each attribute. And then, the hyper-class representation of the data is constructed to learn the weight of the segmented attribute value (hyper-class) for each attribute, so as to construct a piecewise weighting function. In addition, the piecewise weighting function is applied to calculate the similarity between users for a collaborative filtering recommendation. Finally, experiments are conducted to examine the collaborative filtering recommendation algorithm, and show that the proposed algorithm with piecewise weighting functions is more efficient than the compared algorithm with fixed weight values, in terms of Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Precision.</p>

show abstract