ML schema: exposing the semantics of machine learning with schemas and ontologies

Gustavo Correa Publio, Diego Esteves, Agnieszka Ławrynowicz, Panče Panov, Larisa Soldatova, Tommaso Soru, J. Vanschoren, Hamid Zafar

Research output: Contribution to conferencePaperAcademic

Abstract

The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms, datasets, and experiments. It can be easily extended and specialized and it is also mapped to other more domain-specific ontologies developed in the area of machine learning and data mining. In this paper we overview existing machine learning interchange formats and present the first release of ML-Schema, a canonical format resulted of more than seven years of experience among different research institutions. We argue that exposing semantics of machine learning algorithms, models, and experiments through a canonical format may pave the way to better interpretability and to realistically achieve the full interoperability of experiments.

Fingerprint

Ontology
Learning systems
Semantics
Learning algorithms
Experiments
Interchanges
Interoperability
Data mining

Keywords

  • ontologies
  • semantic web
  • machine learning

Cite this

Correa Publio, G., Esteves, D., Ławrynowicz, A., Panov, P., Soldatova, L., Soru, T., ... Zafar, H. (2018). ML schema: exposing the semantics of machine learning with schemas and ontologies. Paper presented at ICML 2018 Workshop on Reproducibility in Machine Learning, .
Correa Publio, Gustavo ; Esteves, Diego ; Ławrynowicz, Agnieszka ; Panov, Panče ; Soldatova, Larisa ; Soru, Tommaso ; Vanschoren, J. ; Zafar, Hamid. / ML schema : exposing the semantics of machine learning with schemas and ontologies. Paper presented at ICML 2018 Workshop on Reproducibility in Machine Learning, .5 p.
@conference{2f9a12bcceb1454da395478a45b70da0,
title = "ML schema: exposing the semantics of machine learning with schemas and ontologies",
abstract = "The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms, datasets, and experiments. It can be easily extended and specialized and it is also mapped to other more domain-specific ontologies developed in the area of machine learning and data mining. In this paper we overview existing machine learning interchange formats and present the first release of ML-Schema, a canonical format resulted of more than seven years of experience among different research institutions. We argue that exposing semantics of machine learning algorithms, models, and experiments through a canonical format may pave the way to better interpretability and to realistically achieve the full interoperability of experiments.",
keywords = "ontologies, semantic web, machine learning",
author = "{Correa Publio}, Gustavo and Diego Esteves and Agnieszka Ławrynowicz and Panče Panov and Larisa Soldatova and Tommaso Soru and J. Vanschoren and Hamid Zafar",
year = "2018",
language = "English",
note = "ICML 2018 Workshop on Reproducibility in Machine Learning ; Conference date: 14-07-2018 Through 14-07-2018",
url = "https://mltrain.cc/events/enabling-reproducibility-in-machine-learning-mltrainrml-icml-2018/",

}

Correa Publio, G, Esteves, D, Ławrynowicz, A, Panov, P, Soldatova, L, Soru, T, Vanschoren, J & Zafar, H 2018, 'ML schema: exposing the semantics of machine learning with schemas and ontologies' Paper presented at ICML 2018 Workshop on Reproducibility in Machine Learning, 14/07/18 - 14/07/18, .

ML schema : exposing the semantics of machine learning with schemas and ontologies. / Correa Publio, Gustavo; Esteves, Diego; Ławrynowicz, Agnieszka; Panov, Panče; Soldatova, Larisa; Soru, Tommaso; Vanschoren, J.; Zafar, Hamid.

2018. Paper presented at ICML 2018 Workshop on Reproducibility in Machine Learning, .

Research output: Contribution to conferencePaperAcademic

TY - CONF

T1 - ML schema

T2 - exposing the semantics of machine learning with schemas and ontologies

AU - Correa Publio,Gustavo

AU - Esteves,Diego

AU - Ławrynowicz,Agnieszka

AU - Panov,Panče

AU - Soldatova,Larisa

AU - Soru,Tommaso

AU - Vanschoren,J.

AU - Zafar,Hamid

PY - 2018

Y1 - 2018

N2 - The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms, datasets, and experiments. It can be easily extended and specialized and it is also mapped to other more domain-specific ontologies developed in the area of machine learning and data mining. In this paper we overview existing machine learning interchange formats and present the first release of ML-Schema, a canonical format resulted of more than seven years of experience among different research institutions. We argue that exposing semantics of machine learning algorithms, models, and experiments through a canonical format may pave the way to better interpretability and to realistically achieve the full interoperability of experiments.

AB - The ML-Schema, proposed by the W3C Machine Learning Schema Community Group, is a top-level ontology that provides a set of classes, properties, and restrictions for representing and interchanging information on machine learning algorithms, datasets, and experiments. It can be easily extended and specialized and it is also mapped to other more domain-specific ontologies developed in the area of machine learning and data mining. In this paper we overview existing machine learning interchange formats and present the first release of ML-Schema, a canonical format resulted of more than seven years of experience among different research institutions. We argue that exposing semantics of machine learning algorithms, models, and experiments through a canonical format may pave the way to better interpretability and to realistically achieve the full interoperability of experiments.

KW - ontologies

KW - semantic web

KW - machine learning

M3 - Paper

ER -

Correa Publio G, Esteves D, Ławrynowicz A, Panov P, Soldatova L, Soru T et al. ML schema: exposing the semantics of machine learning with schemas and ontologies. 2018. Paper presented at ICML 2018 Workshop on Reproducibility in Machine Learning, .