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

TL;DR

This paper introduces an end-to-end method for dynamic feature acquisition in medical time series, aiming to optimize measurement timing and selection to reduce costs while maintaining predictive performance.

Contribution

It proposes a novel approach based on maximizing conditional mutual information, trained solely with downstream loss, to improve feature acquisition policies.

Findings

Outperforms random acquisition policies

Matches unrestrained budget models in performance

Does not yet surpass static acquisition strategies

Abstract

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.