NEVO-GSPT: Population-Based Neural Network Evolution Using Inflate and Deflate Operators

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Farinati, Davide, Santos, Frederico J. J. B., Vanneschi, Leonardo, Castelli, Mauro
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918286149550080
author Farinati, Davide
Santos, Frederico J. J. B.
Vanneschi, Leonardo
Castelli, Mauro
author_facet Farinati, Davide
Santos, Frederico J. J. B.
Vanneschi, Leonardo
Castelli, Mauro
contents Evolving neural network architectures is a computationally demanding process. Traditional methods often require an extensive search through large architectural spaces and offer limited understanding of how structural modifications influence model behavior. This paper introduces \gls{ngspt}, a novel Neuroevolution algorithm based on two key innovations. First, we adapt geometric semantic operators~(GSOs) from genetic programming to neural network evolution, ensuring that architectural changes produce predictable effects on network semantics within a unimodal error surface. Second, we introduce a novel operator (DGSM) that enables controlled reduction of network size, while maintaining the semantic properties of~GSOs. Unlike traditional approaches, \gls{ngspt}'s efficient evaluation mechanism, which only requires computing the semantics of newly added components, allows for efficient population-based training, resulting in a comprehensive exploration of the search space at a fraction of the computational cost. Experimental results on four regression benchmarks show that \gls{ngspt} consistently evolves compact neural networks that achieve performance comparable to or better than established methods in the literature, such as standard neural networks, SLIM-GSGP, TensorNEAT, and SLM.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08657
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NEVO-GSPT: Population-Based Neural Network Evolution Using Inflate and Deflate Operators
Farinati, Davide
Santos, Frederico J. J. B.
Vanneschi, Leonardo
Castelli, Mauro
Neural and Evolutionary Computing
Evolving neural network architectures is a computationally demanding process. Traditional methods often require an extensive search through large architectural spaces and offer limited understanding of how structural modifications influence model behavior. This paper introduces \gls{ngspt}, a novel Neuroevolution algorithm based on two key innovations. First, we adapt geometric semantic operators~(GSOs) from genetic programming to neural network evolution, ensuring that architectural changes produce predictable effects on network semantics within a unimodal error surface. Second, we introduce a novel operator (DGSM) that enables controlled reduction of network size, while maintaining the semantic properties of~GSOs. Unlike traditional approaches, \gls{ngspt}'s efficient evaluation mechanism, which only requires computing the semantics of newly added components, allows for efficient population-based training, resulting in a comprehensive exploration of the search space at a fraction of the computational cost. Experimental results on four regression benchmarks show that \gls{ngspt} consistently evolves compact neural networks that achieve performance comparable to or better than established methods in the literature, such as standard neural networks, SLIM-GSGP, TensorNEAT, and SLM.
title NEVO-GSPT: Population-Based Neural Network Evolution Using Inflate and Deflate Operators
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2601.08657