mlsanityData to 7 Oct 2026

Bayesian Active Learning By Distribution Disagreement

arXiv 2501.01248 ↗First posted 2 Jan 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Active Learning (AL) for regression has been systematically under-researched due to the increased difficulty of measuring uncertainty in regression models. Since normalizing flows offer a full predictive distribution instead of a point forecast, they facilitate direct usage of known heuristics for AL like Entropy or Least-Confident sampling. However, we show that most of these heuristics do not work well for normalizing flows in pool-based AL and we need more sophisticated algorithms to distinguish between aleatoric and epistemic uncertainty. In this work we propose BALSA, an adaptation of the BALD algorithm, tailored for regression with normalizing flows. With this work we extend current research on uncertainty quantification with normalizing flows citeberry2023normalizing, berry2023escaping to real world data and pool-based AL with multiple acquisition functions and query sizes. We report SOTA results for BALSA across 4 different datasets and 2 different architectures.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 20 references that are in the map. First posted on arXiv 2 Jan 2025.

Builds on

11 of 20 references.

References · 11

  1. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  2. 2017Deep Bayesian Active Learning with Image Datacited by 812
  3. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  4. 2019Neural Spline Flowscited by 590
  5. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  6. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 131
  7. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  8. 2022Bayesian Active Learning with Fully Bayesian Gaussian Processescited by 26
  9. 2023Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessmentcited by 25
  10. 2023ActiveGLAE: A Benchmark for Deep Active Learning with Transformerscited by 14
  11. 2023Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modelingcited by 10

Built on by

Not cited yet.