Saved in:
Bibliographic Details
Main Authors: Chen, Xiaotian, Liu, Hongyun, Ziabari, Seyed Sahand Mohammadi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.09204
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913889124352000
author Chen, Xiaotian
Liu, Hongyun
Ziabari, Seyed Sahand Mohammadi
author_facet Chen, Xiaotian
Liu, Hongyun
Ziabari, Seyed Sahand Mohammadi
contents Deep Neural Networks (DNNs) have been proven to be exceptionally effective and have been applied across diverse domains within deep learning. However, as DNN models increase in complexity, the demand for reduced computational costs and memory overheads has become increasingly urgent. Sparsity has emerged as a leading approach in this area. The robustness of sparse Multi-layer Perceptrons (MLPs) for supervised feature selection, along with the application of Sparse Evolutionary Training (SET), illustrates the feasibility of reducing computational costs without compromising accuracy. Moreover, it is believed that the SET algorithm can still be improved through a structural optimization method called motif-based optimization, with potential efficiency gains exceeding 40% and a performance decline of under 4%. This research investigates whether the structural optimization of Sparse Evolutionary Training applied to Multi-layer Perceptrons (SET-MLP) can enhance performance and to what extent this improvement can be achieved.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09204
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Topological Improvement of the Overall Performance of Sparse Evolutionary Training: Motif-Based Structural Optimization of Sparse MLPs Project
Chen, Xiaotian
Liu, Hongyun
Ziabari, Seyed Sahand Mohammadi
Neural and Evolutionary Computing
Artificial Intelligence
Deep Neural Networks (DNNs) have been proven to be exceptionally effective and have been applied across diverse domains within deep learning. However, as DNN models increase in complexity, the demand for reduced computational costs and memory overheads has become increasingly urgent. Sparsity has emerged as a leading approach in this area. The robustness of sparse Multi-layer Perceptrons (MLPs) for supervised feature selection, along with the application of Sparse Evolutionary Training (SET), illustrates the feasibility of reducing computational costs without compromising accuracy. Moreover, it is believed that the SET algorithm can still be improved through a structural optimization method called motif-based optimization, with potential efficiency gains exceeding 40% and a performance decline of under 4%. This research investigates whether the structural optimization of Sparse Evolutionary Training applied to Multi-layer Perceptrons (SET-MLP) can enhance performance and to what extent this improvement can be achieved.
title A Topological Improvement of the Overall Performance of Sparse Evolutionary Training: Motif-Based Structural Optimization of Sparse MLPs Project
topic Neural and Evolutionary Computing
Artificial Intelligence
url https://arxiv.org/abs/2506.09204