paper-with-me

홈 › Papers

Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not

2021-12-13 · NeurIPS Workshop ICBINB 2021 12 · Chelsea Murray, James U. Allingham, Javier Antorán, José Miguel Hernández-Lobato

Farquhar et al. [2021] show that correcting for active learning bias with underparameterised models leads to improved downstream performance. For overparameterised models such as NNs, however, correction leads either to decreased or unchanged performance. They suggest that this is due to an "overfitting bias" which offsets the active learning bias. We show that depth uncertainty networks operate in a low overfitting regime, much like underparameterised models. They should therefore see an increase in performance with bias correction. Surprisingly, they do not. We propose that this negative result, as well as the results Farquhar et al. [2021], can be explained via the lens of the bias-variance decomposition of generalisation error.

📄 PDF Abstract BibTeX arXiv:2112.06926

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

Depth Uncertainty Networks for Active Learning

2021-12-13 · Chelsea Murray, James U. Allingham, Javier Antorán, José Miguel Hernández-Lobato

In active learning, the size and complexity of the training dataset changes over time. Simple models that are well specified by the amount of data available at the start of active learning might suffer from bias as more …

Active Learning

DEUX: Active Exploration for Learning Unsupervised Depth Perception

2023-09-16 · Marvin Chancán, Alex Wong, Ian Abraham

Depth perception models are typically trained on non-interactive datasets with predefined camera trajectories. However, this often introduces systematic biases into the learning process correlated to specific camera path…

Depth CompletionDepth EstimationMotion PlanningRobot Navigation+1

Interpretable Active Learning

2017-07-31 · Richard L. Phillips, Kyu Hyun Chang, Sorelle A. Friedler

Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has…

Active Learning

Can Active Learning Preemptively Mitigate Fairness Issues?

2021-04-14 · Frédéric Branchaud-Charron, Parmida Atighehchian, Pau Rodríguez, Grace Abuhamad 외

Dataset bias is one of the prevailing causes of unfairness in machine learning. Addressing fairness at the data collection and dataset preparation stages therefore becomes an essential part of training fairer algorithms.…

Active LearningFairness

Multi-Label Bayesian Active Learning with Inter-Label Relationships

2024-11-26 · Yuanyuan Qi, Jueqing Lu, Xiaohao Yang, Joanne Enticott 외

The primary challenge of multi-label active learning, differing it from multi-class active learning, lies in assessing the informativeness of an indefinite number of labels while also accounting for the inherited label c…

Active LearningDiversityInformativeness