Topological Feature Selection

Antonio Briola, Tomaso Aste
Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML), PMLR 221:534-556, 2023.

Abstract

In this paper, we introduce a novel unsupervised, graph-based filter feature selection technique which exploits the power of topologically constrained network representations. We model dependency structures among features using a family of chordal graphs (i.e. the Triangulated Maximally Filtered Graph), and we maximise the likelihood of features’ relevance by studying their relative position inside the network. Such an approach presents three aspects that are particularly satisfactory compared to its alternatives: (i) it is highly tunable and easily adaptable to the nature of input data; (ii) it is fully explainable, maintaining, at the same time, a remarkable level of simplicity; (iii) it is computationally cheap. We test our algorithm on $16$ benchmark datasets from different application domains showing that it outperforms or matches the current state-of-the-art under heterogeneous evaluation conditions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v221-briola23a, title = {Topological Feature Selection}, author = {Briola, Antonio and Aste, Tomaso}, booktitle = {Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML)}, pages = {534--556}, year = {2023}, editor = {Doster, Timothy and Emerson, Tegan and Kvinge, Henry and Miolane, Nina and Papillon, Mathilde and Rieck, Bastian and Sanborn, Sophia}, volume = {221}, series = {Proceedings of Machine Learning Research}, month = {28 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v221/briola23a/briola23a.pdf}, url = {https://proceedings.mlr.press/v221/briola23a.html}, abstract = {In this paper, we introduce a novel unsupervised, graph-based filter feature selection technique which exploits the power of topologically constrained network representations. We model dependency structures among features using a family of chordal graphs (i.e. the Triangulated Maximally Filtered Graph), and we maximise the likelihood of features’ relevance by studying their relative position inside the network. Such an approach presents three aspects that are particularly satisfactory compared to its alternatives: (i) it is highly tunable and easily adaptable to the nature of input data; (ii) it is fully explainable, maintaining, at the same time, a remarkable level of simplicity; (iii) it is computationally cheap. We test our algorithm on $16$ benchmark datasets from different application domains showing that it outperforms or matches the current state-of-the-art under heterogeneous evaluation conditions.} }
Endnote
%0 Conference Paper %T Topological Feature Selection %A Antonio Briola %A Tomaso Aste %B Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML) %C Proceedings of Machine Learning Research %D 2023 %E Timothy Doster %E Tegan Emerson %E Henry Kvinge %E Nina Miolane %E Mathilde Papillon %E Bastian Rieck %E Sophia Sanborn %F pmlr-v221-briola23a %I PMLR %P 534--556 %U https://proceedings.mlr.press/v221/briola23a.html %V 221 %X In this paper, we introduce a novel unsupervised, graph-based filter feature selection technique which exploits the power of topologically constrained network representations. We model dependency structures among features using a family of chordal graphs (i.e. the Triangulated Maximally Filtered Graph), and we maximise the likelihood of features’ relevance by studying their relative position inside the network. Such an approach presents three aspects that are particularly satisfactory compared to its alternatives: (i) it is highly tunable and easily adaptable to the nature of input data; (ii) it is fully explainable, maintaining, at the same time, a remarkable level of simplicity; (iii) it is computationally cheap. We test our algorithm on $16$ benchmark datasets from different application domains showing that it outperforms or matches the current state-of-the-art under heterogeneous evaluation conditions.
APA
Briola, A. & Aste, T.. (2023). Topological Feature Selection. Proceedings of 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML), in Proceedings of Machine Learning Research 221:534-556 Available from https://proceedings.mlr.press/v221/briola23a.html.

Related Material