BenchMake: turn any scientific data set into a reproducible benchmark

Benchmark data sets are a cornerstone of machine learning development and applications, ensuring new methods are robust, reliable and competitive. The relative rarity of benchmark sets in computational science, due to the uniqueness of the problems and the pace of change in the associated domains, m...

Full description

Saved in:
Bibliographic Details
Main Author: A S Barnard
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Machine Learning: Science and Technology
Subjects:
Online Access:https://doi.org/10.1088/2632-2153/adf810
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849399329192673280
author A S Barnard
author_facet A S Barnard
author_sort A S Barnard
collection DOAJ
description Benchmark data sets are a cornerstone of machine learning development and applications, ensuring new methods are robust, reliable and competitive. The relative rarity of benchmark sets in computational science, due to the uniqueness of the problems and the pace of change in the associated domains, makes evaluating new innovations difficult for computational scientists. In this paper a new tool is developed and tested to potentially turn any of the increasing numbers of scientific data sets made openly available into a benchmark accessible to the community. BenchMake uses non-negative matrix factorization to deterministically identify and isolate challenging edge cases on the convex hull (the smallest convex set that contains all existing data instances) and partitions a required fraction of matched data instances into a testing set that maximizes divergence and statistical significance, across tabular, graph, image, signal and textual modalities. BenchMake splits are compared to establish splits and random splits using ten publicly available benchmark sets from different areas of science, with different sizes, shapes, distributions.
format Article
id doaj-art-2ee7b94ca6de43708d096ffc943d049e
institution Kabale University
issn 2632-2153
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series Machine Learning: Science and Technology
spelling doaj-art-2ee7b94ca6de43708d096ffc943d049e2025-08-20T03:38:22ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016303050210.1088/2632-2153/adf810BenchMake: turn any scientific data set into a reproducible benchmarkA S Barnard0https://orcid.org/0000-0002-4784-2382School of Computing, Australian National University , Acton ACT 2601, AustraliaBenchmark data sets are a cornerstone of machine learning development and applications, ensuring new methods are robust, reliable and competitive. The relative rarity of benchmark sets in computational science, due to the uniqueness of the problems and the pace of change in the associated domains, makes evaluating new innovations difficult for computational scientists. In this paper a new tool is developed and tested to potentially turn any of the increasing numbers of scientific data sets made openly available into a benchmark accessible to the community. BenchMake uses non-negative matrix factorization to deterministically identify and isolate challenging edge cases on the convex hull (the smallest convex set that contains all existing data instances) and partitions a required fraction of matched data instances into a testing set that maximizes divergence and statistical significance, across tabular, graph, image, signal and textual modalities. BenchMake splits are compared to establish splits and random splits using ten publicly available benchmark sets from different areas of science, with different sizes, shapes, distributions.https://doi.org/10.1088/2632-2153/adf810scientific databenchmarkarchetypal analysissamplingdata splitmodel evaluation
spellingShingle A S Barnard
BenchMake: turn any scientific data set into a reproducible benchmark
Machine Learning: Science and Technology
scientific data
benchmark
archetypal analysis
sampling
data split
model evaluation
title BenchMake: turn any scientific data set into a reproducible benchmark
title_full BenchMake: turn any scientific data set into a reproducible benchmark
title_fullStr BenchMake: turn any scientific data set into a reproducible benchmark
title_full_unstemmed BenchMake: turn any scientific data set into a reproducible benchmark
title_short BenchMake: turn any scientific data set into a reproducible benchmark
title_sort benchmake turn any scientific data set into a reproducible benchmark
topic scientific data
benchmark
archetypal analysis
sampling
data split
model evaluation
url https://doi.org/10.1088/2632-2153/adf810
work_keys_str_mv AT asbarnard benchmaketurnanyscientificdatasetintoareproduciblebenchmark