Transferable Candidate Proposal with Bounded Uncertainty
Not on the map. Why?
Abstract (arXiv)
From an empirical perspective, the subset chosen through active learning cannot guarantee an advantage over random sampling when transferred to another model. While it underscores the significance of verifying transferability, experimental design from previous works often neglected that the informativeness of a data subset can change over model configurations. To tackle this issue, we introduce a new experimental design, coined as Candidate Proposal, to find transferable data candidates from which active learning algorithms choose the informative subset. Correspondingly, a data selection algorithm is proposed, namely Transferable candidate proposal with Bounded Uncertainty (TBU), which constrains the pool of transferable data candidates by filtering out the presumably redundant data points based on uncertainty estimation. We verified the validity of TBU in image classification benchmarks, including CIFAR-10/100 and SVHN. When transferred to different model configurations, TBU consistency improves performance in existing active learning algorithms. Our code is available at https://github.com/gokyeongryeol/TBU.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 7 Dec 2023.
Builds on
37 of 46 references.
References · 37
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
- 2017Deep Bayesian Active Learning with Image Datacited by 812
- 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 669
- 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
- 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
- 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
- 2020A Survey of Deep Active Learningcited by 547
- 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
25 more
- 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
- 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
- 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 368
- 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
- 2019Selection via Proxy: Efficient Data Selection for Deep Learningcited by 337
- 2019Learning Loss for Active Learningcited by 335
- 2021Curriculum Learning: A Surveycited by 257
- 2021A Survey on Deep Semi-supervised Learningcited by 250
- 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
- 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 227
- 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
- 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
- 2019Towards moderate overparameterization: global convergence guarantees for training shallow neural networkscited by 176
- 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
- 2021Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learningcited by 162
- 2022Data Banzhaf: A Robust Data Valuation Framework for Machine Learningcited by 126
- 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
- 2021Influence Selection for Active Learningcited by 82
- 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
- 2021Correlated Input-Dependent Label Noise in Large-Scale Image Classificationcited by 37
- 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
- 2021A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applicationscited by 24
- 2020Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimationcited by 16
- 2023Massively Scaling Heteroscedastic Classifierscited by 11
- 2021Deep Classifiers with Label Noise Modeling and Distance Awarenesscited by 8
Built on by
Citing papers per year: 2025: 2.
2 papers.