# Model-Agnostic Dynamic Feature Selection with Uncertainty Quantification

arXiv: https://arxiv.org/abs/2508.02566 · HTML: https://mlsanity.com/paper/2508.02566/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness](https://mlsanity.com/paper/2006.10108/) (2020)
- [Efficient parametrization of multi-domain deep neural networks](https://mlsanity.com/paper/1803.10082/) (2018)
- [Uncertainty Quantification and Deep Ensembles](https://mlsanity.com/paper/2007.08792/) (2020)
- [Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?](https://mlsanity.com/paper/2209.03302/) (2022)
- [EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE](https://mlsanity.com/paper/1809.11142/) (2018)
- [A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement](https://mlsanity.com/paper/2204.09308/) (2022)
- [Learning to Maximize Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2301.00557/) (2023)
- [Classification with Costly Features using Deep Reinforcement Learning](https://mlsanity.com/paper/1711.07364/) (2017)
- [Variational Information Pursuit for Interpretable Predictions](https://mlsanity.com/paper/2302.02876/) (2023)
- [Estimating Conditional Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2306.03301/) (2023)
- [The Missing Indicator Method: From Low to High Dimensions](https://mlsanity.com/paper/2211.09259/) (2022)
- [What makes an Ensemble (Un) Interpretable?](https://mlsanity.com/paper/2506.08216/) (2025)
- [Dynamic Feature Selection from Variable Feature Sets Using Features of Features](https://mlsanity.com/paper/2503.09181/) (2025)

## Built on by (most cited first, 1 of 1)

- [Hypernetworks for Dynamic Feature Selection](https://mlsanity.com/paper/2605.12278/) (2026)

## Abstract (arXiv)

Dynamic feature selection (DFS) addresses budget constraints in decision-making by sequentially acquiring features for each instance, making it appealing for resource-limited scenarios. However, existing DFS methods require models specifically designed for the sequential acquisition setting, limiting compatibility with models already deployed in practice. Furthermore, they provide limited uncertainty quantification, undermining trust in high-stakes decisions. In this work, we show that DFS introduces new uncertainty sources compared to the static setting. We formalise how model adaptation to feature subsets induces epistemic uncertainty, how standard imputation strategies bias aleatoric uncertainty estimation, and why predictive confidence fails to discriminate between good and bad selection policies. We also propose a model-agnostic DFS framework compatible with pre-trained classifiers, including interpretable-by-design models, through efficient subset reparametrization strategies. Empirical evaluation on tabular and image datasets demonstrates competitive accuracy against state-of-the-art greedy and reinforcement learning-based DFS methods with both neural and rule-based classifiers. We further show that the identified uncertainty sources persist across most existing approaches, highlighting the need for uncertainty-aware DFS.