Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sergeev, Fedor, Malsot, Paola, Rätsch, Gunnar, Fortuin, Vincent
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929426448515072
author Sergeev, Fedor
Malsot, Paola
Rätsch, Gunnar
Fortuin, Vincent
author_facet Sergeev, Fedor
Malsot, Paola
Rätsch, Gunnar
Fortuin, Vincent
contents Knowing which features of a multivariate time series to measure and when is a key task in medicine, wearables, and robotics. Better acquisition policies can reduce costs while maintaining or even improving the performance of downstream predictors. Inspired by the maximization of conditional mutual information, we propose an approach to train acquirers end-to-end using only the downstream loss. We show that our method outperforms random acquisition policy, matches a model with an unrestrained budget, but does not yet overtake a static acquisition strategy. We highlight the assumptions and outline avenues for future work.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13429
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information
Sergeev, Fedor
Malsot, Paola
Rätsch, Gunnar
Fortuin, Vincent
Machine Learning
Artificial Intelligence
Knowing which features of a multivariate time series to measure and when is a key task in medicine, wearables, and robotics. Better acquisition policies can reduce costs while maintaining or even improving the performance of downstream predictors. Inspired by the maximization of conditional mutual information, we propose an approach to train acquirers end-to-end using only the downstream loss. We show that our method outperforms random acquisition policy, matches a model with an unrestrained budget, but does not yet overtake a static acquisition strategy. We highlight the assumptions and outline avenues for future work.
title Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2407.13429