Select High-Level Features: Efficient Experts from a Hierarchical Classification Network

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kelm, André, Hannemann, Niels, Heberle, Bruno, Schmidt, Lucas, Rolff, Tim, Wilms, Christian, Yaghoubi, Ehsan, Frintrop, Simone
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915026863915008
author Kelm, André
Hannemann, Niels
Heberle, Bruno
Schmidt, Lucas
Rolff, Tim
Wilms, Christian
Yaghoubi, Ehsan
Frintrop, Simone
author_facet Kelm, André
Hannemann, Niels
Heberle, Bruno
Schmidt, Lucas
Rolff, Tim
Wilms, Christian
Yaghoubi, Ehsan
Frintrop, Simone
contents This study introduces a novel expert generation method that dynamically reduces task and computational complexity without compromising predictive performance. It is based on a new hierarchical classification network topology that combines sequential processing of generic low-level features with parallelism and nesting of high-level features. This structure allows for the innovative extraction technique: the ability to select only high-level features of task-relevant categories. In certain cases, it is possible to skip almost all unneeded high-level features, which can significantly reduce the inference cost and is highly beneficial in resource-constrained conditions. We believe this method paves the way for future network designs that are lightweight and adaptable, making them suitable for a wide range of applications, from compact edge devices to large-scale clouds. In terms of dynamic inference our methodology can achieve an exclusion of up to 88.7\,\% of parameters and 73.4\,\% fewer giga-multiply accumulate (GMAC) operations, analysis against comparative baselines showing an average reduction of 47.6\,\% in parameters and 5.8\,\% in GMACs across the cases we evaluated.
format Preprint
id arxiv_https___arxiv_org_abs_2403_05601
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Select High-Level Features: Efficient Experts from a Hierarchical Classification Network
Kelm, André
Hannemann, Niels
Heberle, Bruno
Schmidt, Lucas
Rolff, Tim
Wilms, Christian
Yaghoubi, Ehsan
Frintrop, Simone
Machine Learning
This study introduces a novel expert generation method that dynamically reduces task and computational complexity without compromising predictive performance. It is based on a new hierarchical classification network topology that combines sequential processing of generic low-level features with parallelism and nesting of high-level features. This structure allows for the innovative extraction technique: the ability to select only high-level features of task-relevant categories. In certain cases, it is possible to skip almost all unneeded high-level features, which can significantly reduce the inference cost and is highly beneficial in resource-constrained conditions. We believe this method paves the way for future network designs that are lightweight and adaptable, making them suitable for a wide range of applications, from compact edge devices to large-scale clouds. In terms of dynamic inference our methodology can achieve an exclusion of up to 88.7\,\% of parameters and 73.4\,\% fewer giga-multiply accumulate (GMAC) operations, analysis against comparative baselines showing an average reduction of 47.6\,\% in parameters and 5.8\,\% in GMACs across the cases we evaluated.
title Select High-Level Features: Efficient Experts from a Hierarchical Classification Network
topic Machine Learning
url https://arxiv.org/abs/2403.05601