Valid interpretation of feature relevance for linear data mappings

Benoît Frenay, Daniela Hofmann, Alexander Schulz, Michael Biehl, Barbara Hammer

Résultats de recherche: Contribution dans un livre/un catalogue/un rapport/dans les actes d'une conférenceArticle dans les actes d'une conférence/un colloque

Résumé

Linear data transformations constitute essential operations in various machine learning algorithms, ranging from linear regression up to adaptive metric transformation. Often, linear scalings are not only used to improve the model accuracy, rather feature coefficients as provided by the mapping are interpreted as an indicator for the relevance of the feature for the task at hand. This principle, however, can be misleading in particular for high-dimensional or correlated features, since it easily marks irrelevant features as relevant or vice versa. In this contribution, we propose a mathematical formalisation of the minimum and maximum feature relevance for a given linear transformation which can efficiently be solved by means of linear programming. We evaluate the method in several benchmarks, where it becomes apparent that the minimum and maximum relevance closely resembles what is often referred to as weak and strong relevance of the features; hence unlike the mere scaling provided by the linear mapping, it ensures valid interpretability.

langue originaleAnglais
titreIEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIDM 2014: 2014 IEEE Symposium on Computational Intelligence and Data Mining, Proceedings
EditeurInstitute of Electrical and Electronics Engineers Inc.
Pages149-156
Nombre de pages8
ISBN (imprimé)9781479945191
Les DOIs
Etat de la publicationPublié - 13 janv. 2015
Evénement5th IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2014 - Orlando, États-Unis
Durée: 9 déc. 201412 déc. 2014

Une conférence

Une conférence5th IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2014
PaysÉtats-Unis
La villeOrlando
période9/12/1412/12/14

Empreinte digitale Examiner les sujets de recherche de « Valid interpretation of feature relevance for linear data mappings ». Ensemble, ils forment une empreinte digitale unique.

  • Contient cette citation

    Frenay, B., Hofmann, D., Schulz, A., Biehl, M., & Hammer, B. (2015). Valid interpretation of feature relevance for linear data mappings. Dans IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIDM 2014: 2014 IEEE Symposium on Computational Intelligence and Data Mining, Proceedings (p. 149-156). [7008661] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIDM.2014.7008661