Inherently Interpretable Time Series Classification via Multiple Instance Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Early, Joseph, Cheung, Gavin KC, Cutajar, Kurt, Xie, Hanting, Kandola, Jas, Twomey, Niall
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916160746815488
author Early, Joseph
Cheung, Gavin KC
Cutajar, Kurt
Xie, Hanting
Kandola, Jas
Twomey, Niall
author_facet Early, Joseph
Cheung, Gavin KC
Cutajar, Kurt
Xie, Hanting
Kandola, Jas
Twomey, Niall
contents Conventional Time Series Classification (TSC) methods are often black boxes that obscure inherent interpretation of their decision-making processes. In this work, we leverage Multiple Instance Learning (MIL) to overcome this issue, and propose a new framework called MILLET: Multiple Instance Learning for Locally Explainable Time series classification. We apply MILLET to existing deep learning TSC models and show how they become inherently interpretable without compromising (and in some cases, even improving) predictive performance. We evaluate MILLET on 85 UCR TSC datasets and also present a novel synthetic dataset that is specially designed to facilitate interpretability evaluation. On these datasets, we show MILLET produces sparse explanations quickly that are of higher quality than other well-known interpretability methods. To the best of our knowledge, our work with MILLET, which is available on GitHub (https://github.com/JAEarly/MILTimeSeriesClassification), is the first to develop general MIL methods for TSC and apply them to an extensive variety of domains
format Preprint
id arxiv_https___arxiv_org_abs_2311_10049
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Inherently Interpretable Time Series Classification via Multiple Instance Learning
Early, Joseph
Cheung, Gavin KC
Cutajar, Kurt
Xie, Hanting
Kandola, Jas
Twomey, Niall
Machine Learning
Artificial Intelligence
Conventional Time Series Classification (TSC) methods are often black boxes that obscure inherent interpretation of their decision-making processes. In this work, we leverage Multiple Instance Learning (MIL) to overcome this issue, and propose a new framework called MILLET: Multiple Instance Learning for Locally Explainable Time series classification. We apply MILLET to existing deep learning TSC models and show how they become inherently interpretable without compromising (and in some cases, even improving) predictive performance. We evaluate MILLET on 85 UCR TSC datasets and also present a novel synthetic dataset that is specially designed to facilitate interpretability evaluation. On these datasets, we show MILLET produces sparse explanations quickly that are of higher quality than other well-known interpretability methods. To the best of our knowledge, our work with MILLET, which is available on GitHub (https://github.com/JAEarly/MILTimeSeriesClassification), is the first to develop general MIL methods for TSC and apply them to an extensive variety of domains
title Inherently Interpretable Time Series Classification via Multiple Instance Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2311.10049