Bayesian Active Learning By Distribution Disagreement
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 \cite{berry2023normalizing, 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.
Code (1)
Tasks
Active LearningregressionUncertainty QuantificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Bayesian Active Learning for Censored Regression
Bayesian active learning is based on information theoretical approaches that focus on maximising the information that new observations provide to the model parameters. This is commonly done by maximising the Bayesian Act…
Active LearningregressionBayesian Active Learning by Disagreements: A Geometric Perspective
We present geometric Bayesian active learning by disagreements (GBALD), a framework that performs BALD on its core-set construction interacting with model uncertainty estimation. Technically, GBALD constructs core-set on…
Active LearningMitigating Sampling Bias and Improving Robustness in Active Learning
This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness. We introduce supervised contrastive active learning by leverag…
Active LearningSelf-Correcting Bayesian Optimization through Bayesian Active Learning
Gaussian processes are the model of choice in Bayesian optimization and active learning. Yet, they are highly dependent on cleverly chosen hyperparameters to reach their full potential, and little effort is devoted to fi…
Active LearningBayesian OptimizationGaussian ProcessesBatch Bayesian Active Learning with Partial Batch Label Sampling
Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice of which to use. Bayesian-based active learning offers principled objectives wi…
Active Learning