mlsanityData to 14 Oct 2026

Towards Robust Active Feature Acquisition

arXiv 2107.04163 ↗First posted 9 Jul 2021cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Truly intelligent systems are expected to make critical decisions with incomplete and uncertain data. Active feature acquisition (AFA), where features are sequentially acquired to improve the prediction, is a step towards this goal. However, current AFA models all deal with a small set of candidate features and have difficulty scaling to a large feature space. Moreover, they are ignorant about the valid domains where they can predict confidently, thus they can be vulnerable to out-of-distribution (OOD) inputs. In order to remedy these deficiencies and bring AFA models closer to practical use, we propose several techniques to advance the current AFA approaches. Our framework can easily handle a large number of features using a hierarchical acquisition policy and is more robust to OOD inputs with the help of an OOD detector for partially observed data. Extensive experiments demonstrate the efficacy of our framework over strong baselines.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 9 Jul 2021.

Builds on

23 of 48 references.

References · 23

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  7. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  8. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  9. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  10. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  11. 2019Verified Uncertainty Calibrationcited by 309
  12. 2015Deep Reinforcement Learning in Large Discrete Action Spacescited by 161
11 more
  1. 2018EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAEcited by 87
  2. 2020Density of States Estimation for Out-of-Distribution Detectioncited by 74
  3. 2019Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisitioncited by 56
  4. 2020Active Feature Acquisition with Generative Surrogate Modelscited by 54
  5. 2020Active MR k-space Sampling with Reinforcement Learningcited by 46
  6. 2020Experimental design for MRI by greedy policy searchcited by 40
  7. 2020Uncertainty Estimation Using a Single Deep Deterministic Neural Networkcited by 37
  8. 2020Multiscale Score Matching for Out-of-Distribution Detectioncited by 36
  9. 2019Flow Models for Arbitrary Conditional Likelihoodscited by 30
  10. 2016Active Information Acquisitioncited by 11
  11. 2020Exact Reduction of Huge Action Spaces in General Reinforcement Learningcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 1; 2026: 2.

5 papers.

  1. 2023Evaluation of Active Feature Acquisition Methods for Time-varying Feature Settingscited by 9
  2. 2024MINT: A wrapper to make multi-modal and multi-image AI models interactivecited by 2
  3. 2025PRECISE-AS: Personalized Reinforcement Learning for Efficient Point-of-Care Echocardiography in Aortic Stenosis Diagnosiscited by 2
  4. 2026Optimizing Point-of-Care Ultrasound Video Acquisition for Probabilistic Multi-Task Heart Failure Detectioncited by 0
  5. 2026AFA-BANDIT: Provably Near-Optimal Online Multi-Feature Classification Under Budget Constraintscited by 0