A Metric for the Balance of Information in Graph Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Davies, Alex O., Ajmeri, Nirav S., Filho, Telmo de Menezes e Silva
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910807293427712
author Davies, Alex O.
Ajmeri, Nirav S.
Filho, Telmo de Menezes e Silva
author_facet Davies, Alex O.
Ajmeri, Nirav S.
Filho, Telmo de Menezes e Silva
contents Graph learning on molecules makes use of information from both the molecular structure and the features attached to that structure. Much work has been conducted on biasing either towards structure or features, with the aim that bias bolsters performance. Identifying which information source a dataset favours, and therefore how to approach learning that dataset, is an open issue. Here we propose Noise-Noise Ratio Difference (NNRD), a quantitative metric for whether there is more useful information in structure or features. By employing iterative noising on features and structure independently, leaving the other intact, NNRD measures the degradation of information in each. We employ NNRD over a range of molecular tasks, and show that it corresponds well to a loss of information, with intuitive results that are more expressive than simple performance aggregates. Our future work will focus on expanding data domains, tasks and types, as well as refining our choice of baseline model.
format Preprint
id arxiv_https___arxiv_org_abs_2501_19137
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Metric for the Balance of Information in Graph Learning
Davies, Alex O.
Ajmeri, Nirav S.
Filho, Telmo de Menezes e Silva
Machine Learning
Artificial Intelligence
Graph learning on molecules makes use of information from both the molecular structure and the features attached to that structure. Much work has been conducted on biasing either towards structure or features, with the aim that bias bolsters performance. Identifying which information source a dataset favours, and therefore how to approach learning that dataset, is an open issue. Here we propose Noise-Noise Ratio Difference (NNRD), a quantitative metric for whether there is more useful information in structure or features. By employing iterative noising on features and structure independently, leaving the other intact, NNRD measures the degradation of information in each. We employ NNRD over a range of molecular tasks, and show that it corresponds well to a loss of information, with intuitive results that are more expressive than simple performance aggregates. Our future work will focus on expanding data domains, tasks and types, as well as refining our choice of baseline model.
title A Metric for the Balance of Information in Graph Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.19137