A Framework for Improving Scholarly Neural Network Diagrams

TL;DR

This paper investigates how neural network system diagrams are used and perceived in scholarly communication, proposing a framework to enhance their clarity and effectiveness based on empirical studies and analysis of published diagrams.

Contribution

It introduces a novel framework for improving neural network diagrams, grounded in qualitative research and validated through experimental and corpus-based studies.

Findings

High diversity in diagram usage and perception

The framework improves communicative efficacy

Published diagrams linked to citation impact

Abstract

Neural networks are a prevalent and effective machine learning component, and their application is leading to significant scientific progress in many domains. As the field of neural network systems is fast growing, it is important to understand how advances are communicated. Diagrams are key to this, appearing in almost all papers describing novel systems. This paper reports on a study into the use of neural network system diagrams, through interviews, card sorting, and qualitative feedback structured around ecologically-derived examples. We find high diversity of usage, perception and preference in both creation and interpretation of diagrams, examining this in the context of existing design, information visualisation, and user experience guidelines. This interview study is used to derive a framework for improving existing diagrams. This framework is evaluated through a mixed-methods experimental study, and a ``corpus-based'' approach examining properties of published diagrams linking the framework to citations. The studies suggest that the framework captures aspects relating to communicative efficacy of scholarly NN diagrams, and provides simple steps for their implementation.