Cargando…
When less is more powerful: Shapley value attributed ablation with augmented learning for practical time series sensor data classification
Time series sensor data classification tasks often suffer from training data scarcity issue due to the expenses associated with the expert-intervened annotation efforts. For example, Electrocardiogram (ECG) data classification for cardio-vascular disease (CVD) detection requires expensive labeling p...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9683574/ https://www.ncbi.nlm.nih.gov/pubmed/36417477 http://dx.doi.org/10.1371/journal.pone.0277975 |
_version_ | 1784835080059879424 |
---|---|
author | Ukil, Arijit Marin, Leandro Jara, Antonio J. |
author_facet | Ukil, Arijit Marin, Leandro Jara, Antonio J. |
author_sort | Ukil, Arijit |
collection | PubMed |
description | Time series sensor data classification tasks often suffer from training data scarcity issue due to the expenses associated with the expert-intervened annotation efforts. For example, Electrocardiogram (ECG) data classification for cardio-vascular disease (CVD) detection requires expensive labeling procedures with the help of cardiologists. Current state-of-the-art algorithms like deep learning models have shown outstanding performance under the general requirement of availability of large set of training examples. In this paper, we propose Shapley Attributed Ablation with Augmented Learning: ShapAAL, which demonstrates that deep learning algorithm with suitably selected subset of the seen examples or ablating the unimportant ones from the given limited training dataset can ensure consistently better classification performance under augmented training. In ShapAAL, additive perturbed training augments the input space to compensate the scarcity in training examples using Residual Network (ResNet) architecture through perturbation-induced inputs, while Shapley attribution seeks the subset from the augmented training space for better learnability with the goal of better general predictive performance, thanks to the “efficiency” and “null player” axioms of transferable utility games upon which Shapley value game is formulated. In ShapAAL, the subset of training examples that contribute positively to a supervised learning setup is derived from the notion of coalition games using Shapley values associated with each of the given inputs’ contribution into the model prediction. ShapAAL is a novel push-pull deep architecture where the subset selection through Shapley value attribution pushes the model to lower dimension while augmented training augments the learning capability of the model over unseen data. We perform ablation study to provide the empirical evidence of our claim and we show that proposed ShapAAL method consistently outperforms the current baselines and state-of-the-art algorithms for time series sensor data classification tasks from publicly available UCR time series archive that includes different practical important problems like detection of CVDs from ECG data. |
format | Online Article Text |
id | pubmed-9683574 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-96835742022-11-24 When less is more powerful: Shapley value attributed ablation with augmented learning for practical time series sensor data classification Ukil, Arijit Marin, Leandro Jara, Antonio J. PLoS One Research Article Time series sensor data classification tasks often suffer from training data scarcity issue due to the expenses associated with the expert-intervened annotation efforts. For example, Electrocardiogram (ECG) data classification for cardio-vascular disease (CVD) detection requires expensive labeling procedures with the help of cardiologists. Current state-of-the-art algorithms like deep learning models have shown outstanding performance under the general requirement of availability of large set of training examples. In this paper, we propose Shapley Attributed Ablation with Augmented Learning: ShapAAL, which demonstrates that deep learning algorithm with suitably selected subset of the seen examples or ablating the unimportant ones from the given limited training dataset can ensure consistently better classification performance under augmented training. In ShapAAL, additive perturbed training augments the input space to compensate the scarcity in training examples using Residual Network (ResNet) architecture through perturbation-induced inputs, while Shapley attribution seeks the subset from the augmented training space for better learnability with the goal of better general predictive performance, thanks to the “efficiency” and “null player” axioms of transferable utility games upon which Shapley value game is formulated. In ShapAAL, the subset of training examples that contribute positively to a supervised learning setup is derived from the notion of coalition games using Shapley values associated with each of the given inputs’ contribution into the model prediction. ShapAAL is a novel push-pull deep architecture where the subset selection through Shapley value attribution pushes the model to lower dimension while augmented training augments the learning capability of the model over unseen data. We perform ablation study to provide the empirical evidence of our claim and we show that proposed ShapAAL method consistently outperforms the current baselines and state-of-the-art algorithms for time series sensor data classification tasks from publicly available UCR time series archive that includes different practical important problems like detection of CVDs from ECG data. Public Library of Science 2022-11-23 /pmc/articles/PMC9683574/ /pubmed/36417477 http://dx.doi.org/10.1371/journal.pone.0277975 Text en © 2022 Ukil et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Ukil, Arijit Marin, Leandro Jara, Antonio J. When less is more powerful: Shapley value attributed ablation with augmented learning for practical time series sensor data classification |
title | When less is more powerful: Shapley value attributed ablation with augmented learning for practical time series sensor data classification |
title_full | When less is more powerful: Shapley value attributed ablation with augmented learning for practical time series sensor data classification |
title_fullStr | When less is more powerful: Shapley value attributed ablation with augmented learning for practical time series sensor data classification |
title_full_unstemmed | When less is more powerful: Shapley value attributed ablation with augmented learning for practical time series sensor data classification |
title_short | When less is more powerful: Shapley value attributed ablation with augmented learning for practical time series sensor data classification |
title_sort | when less is more powerful: shapley value attributed ablation with augmented learning for practical time series sensor data classification |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9683574/ https://www.ncbi.nlm.nih.gov/pubmed/36417477 http://dx.doi.org/10.1371/journal.pone.0277975 |
work_keys_str_mv | AT ukilarijit whenlessismorepowerfulshapleyvalueattributedablationwithaugmentedlearningforpracticaltimeseriessensordataclassification AT marinleandro whenlessismorepowerfulshapleyvalueattributedablationwithaugmentedlearningforpracticaltimeseriessensordataclassification AT jaraantonioj whenlessismorepowerfulshapleyvalueattributedablationwithaugmentedlearningforpracticaltimeseriessensordataclassification |