An evidence-based guidance framework for neural network system diagrams.

Accurate communication of research is essential. We present the first evidence-based framework for formatting neural network architecture diagrams within scholarly publications. Neural networks are a prevalent and important machine learning component, and their application is leading to significant...

Full description

Saved in:
Bibliographic Details
Main Authors: Guy Marshall, André Freitas, Caroline Jay
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0318800
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225181517578240
author Guy Marshall
André Freitas
Caroline Jay
author_facet Guy Marshall
André Freitas
Caroline Jay
author_sort Guy Marshall
collection DOAJ
description Accurate communication of research is essential. We present the first evidence-based framework for formatting neural network architecture diagrams within scholarly publications. Neural networks are a prevalent and important machine learning component, and their application is leading to significant scientific progress in many domains. Diagrams are key to their communication, appearing in almost all papers describing novel systems. However, there are currently no established, evidenced-based conventions describing how they should be presented. We study the use of neural network system diagrams through interviews, card sorting, and qualitative feedback structured around ecologically-derived example diagrams. We find that diagrams in scholarly publications can be difficult to interpret due to ambiguity and variance in their presentation, and that there is a high diversity of usage, perception and preference in both the creation and interpretation of diagrams. We examine the results in the context of existing design, information visualisation, and user experience guidelines and use this foundation to derive a framework for formatting diagrams, which is evaluated through an experimental study, and a comprehensive "corpus-based" approach examining properties of published diagrams in top neural network venues. The studies demonstrate that 1) both the usability and utility of the framework are high and 2) papers containing diagrams that conform to the guidelines receive more citations than those containing diagrams that violate them.
format Article
id doaj-art-65668ee965a84e1890eac754fce982a8
institution Kabale University
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-65668ee965a84e1890eac754fce982a82025-08-25T05:31:05ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01203e031880010.1371/journal.pone.0318800An evidence-based guidance framework for neural network system diagrams.Guy MarshallAndré FreitasCaroline JayAccurate communication of research is essential. We present the first evidence-based framework for formatting neural network architecture diagrams within scholarly publications. Neural networks are a prevalent and important machine learning component, and their application is leading to significant scientific progress in many domains. Diagrams are key to their communication, appearing in almost all papers describing novel systems. However, there are currently no established, evidenced-based conventions describing how they should be presented. We study the use of neural network system diagrams through interviews, card sorting, and qualitative feedback structured around ecologically-derived example diagrams. We find that diagrams in scholarly publications can be difficult to interpret due to ambiguity and variance in their presentation, and that there is a high diversity of usage, perception and preference in both the creation and interpretation of diagrams. We examine the results in the context of existing design, information visualisation, and user experience guidelines and use this foundation to derive a framework for formatting diagrams, which is evaluated through an experimental study, and a comprehensive "corpus-based" approach examining properties of published diagrams in top neural network venues. The studies demonstrate that 1) both the usability and utility of the framework are high and 2) papers containing diagrams that conform to the guidelines receive more citations than those containing diagrams that violate them.https://doi.org/10.1371/journal.pone.0318800
spellingShingle Guy Marshall
André Freitas
Caroline Jay
An evidence-based guidance framework for neural network system diagrams.
PLoS ONE
title An evidence-based guidance framework for neural network system diagrams.
title_full An evidence-based guidance framework for neural network system diagrams.
title_fullStr An evidence-based guidance framework for neural network system diagrams.
title_full_unstemmed An evidence-based guidance framework for neural network system diagrams.
title_short An evidence-based guidance framework for neural network system diagrams.
title_sort evidence based guidance framework for neural network system diagrams
url https://doi.org/10.1371/journal.pone.0318800
work_keys_str_mv AT guymarshall anevidencebasedguidanceframeworkforneuralnetworksystemdiagrams
AT andrefreitas anevidencebasedguidanceframeworkforneuralnetworksystemdiagrams
AT carolinejay anevidencebasedguidanceframeworkforneuralnetworksystemdiagrams
AT guymarshall evidencebasedguidanceframeworkforneuralnetworksystemdiagrams
AT andrefreitas evidencebasedguidanceframeworkforneuralnetworksystemdiagrams
AT carolinejay evidencebasedguidanceframeworkforneuralnetworksystemdiagrams