Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Chenhui, Wang, Xinyao, Yu, Fuxun, Xiong, Jinjun, Chen, Xiang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.03192
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913344985759744
author Xu, Chenhui
Wang, Xinyao
Yu, Fuxun
Xiong, Jinjun
Chen, Xiang
author_facet Xu, Chenhui
Wang, Xinyao
Yu, Fuxun
Xiong, Jinjun
Chen, Xiang
contents Machine learning is evolving towards high-order models that necessitate pre-training on extensive datasets, a process associated with significant overheads. Traditional models, despite having pre-trained weights, are becoming obsolete due to architectural differences that obstruct the effective transfer and initialization of these weights. To address these challenges, we introduce a novel framework, QuadraNet V2, which leverages quadratic neural networks to create efficient and sustainable high-order learning models. Our method initializes the primary term of the quadratic neuron using a standard neural network, while the quadratic term is employed to adaptively enhance the learning of data non-linearity or shifts. This integration of pre-trained primary terms with quadratic terms, which possess advanced modeling capabilities, significantly augments the information characterization capacity of the high-order network. By utilizing existing pre-trained weights, QuadraNet V2 reduces the required GPU hours for training by 90\% to 98.4\% compared to training from scratch, demonstrating both efficiency and effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03192
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation
Xu, Chenhui
Wang, Xinyao
Yu, Fuxun
Xiong, Jinjun
Chen, Xiang
Machine Learning
Artificial Intelligence
Machine learning is evolving towards high-order models that necessitate pre-training on extensive datasets, a process associated with significant overheads. Traditional models, despite having pre-trained weights, are becoming obsolete due to architectural differences that obstruct the effective transfer and initialization of these weights. To address these challenges, we introduce a novel framework, QuadraNet V2, which leverages quadratic neural networks to create efficient and sustainable high-order learning models. Our method initializes the primary term of the quadratic neuron using a standard neural network, while the quadratic term is employed to adaptively enhance the learning of data non-linearity or shifts. This integration of pre-trained primary terms with quadratic terms, which possess advanced modeling capabilities, significantly augments the information characterization capacity of the high-order network. By utilizing existing pre-trained weights, QuadraNet V2 reduces the required GPU hours for training by 90\% to 98.4\% compared to training from scratch, demonstrating both efficiency and effectiveness.
title QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.03192