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

arXiv: https://arxiv.org/abs/2407.13429 · HTML: https://mlsanity.com/paper/2407.13429/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [Revisiting Active Perception](https://mlsanity.com/paper/1603.02729/) (2016)
- [EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE](https://mlsanity.com/paper/1809.11142/) (2018)
- [Prediction-Oriented Bayesian Active Learning](https://mlsanity.com/paper/2304.08151/) (2023)
- [Learning to Maximize Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2301.00557/) (2023)
- [Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection](https://mlsanity.com/paper/2205.06187/) (2022)
- [Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task](https://mlsanity.com/paper/2211.05039/) (2022)
- [Temporal Label Smoothing for Early Event Prediction](https://mlsanity.com/paper/2208.13764/) (2022)
- [Incorporating Unlabelled Data into Bayesian Neural Networks](https://mlsanity.com/paper/2304.01762/) (2023)
- [On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series](https://mlsanity.com/paper/2311.08902/) (2023)

## Abstract (arXiv)

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.