Pith. sign in

REVIEW 10 cited by

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2202.02794 v4 pith:IVDVXJPV submitted 2022-02-06 cs.LG

Guy Hacohen , Avihu Dekel , Daphna Weinshall This is my paper · ORCID
classification cs.LG
keywords learningtypiclustactivebudgetexamplesstrategiesbestbudgets
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Investigating active learning, we focus on the relation between the number of labeled examples (budget size), and suitable querying strategies. Our theoretical analysis shows a behavior reminiscent of phase transition: typical examples are best queried when the budget is low, while unrepresentative examples are best queried when the budget is large. Combined evidence shows that a similar phenomenon occurs in common classification models. Accordingly, we propose TypiClust -- a deep active learning strategy suited for low budgets. In a comparative empirical investigation of supervised learning, using a variety of architectures and image datasets, TypiClust outperforms all other active learning strategies in the low-budget regime. Using TypiClust in the semi-supervised framework, performance gets an even more significant boost. In particular, state-of-the-art semi-supervised methods trained on CIFAR-10 with 10 labeled examples selected by TypiClust, reach 93.2% accuracy -- an improvement of 39.4% over random selection. Code is available at https://github.com/avihu111/TypiClust.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics

    stat.ML 2026-07 accept novelty 7.0 of 10

    Under Gaussian design with n ≍ d, the empirical distribution of leave-one-out influences for convex M-estimators converges to the pushforward of a four-dimensional Gaussian through an explicit nonlinear map built from...

  2. IntraStyler: Intra-Domain Style Synthesis for Cross-Modality MRI Domain Adaptation

    cs.CV 2026-01 conditional novelty 7.0 of 10

    An exemplar-based style synthesis method that learns scanner-like style vectors via contrastive learning and uses them to generate diverse synthetic T2 images, improving downstream cross-modality segmentation.

  3. One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence

    cs.AI 2026-07 conditional novelty 6.5 of 10

    Past a budget-dependent miscalibration threshold δ* that rises as B/N shrinks, confidence-ranked auditing of LLM agent fleets is worse than random; open-weight models land near the flip while shared difficulty dominat...

  4. Certainty and Uncertainty Guided Active Domain Adaptation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A collaborative active domain adaptation framework that adds confident pseudo-labeled samples alongside uncertainty-based active queries, beating prior ADA methods on Office-Home and DomainNet.

  5. TypiCore: A Hybrid Active Query Strategy for Class-Incremental Learning on Time Series

    cs.LG 2026-07 conditional novelty 5.0 of 10

    TypiCore—alternating typicality- and diversity-based active queries—improves label-efficient class-incremental learning on multivariate time-series benchmarks.

  6. VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning

    cs.CV 2026-03 conditional novelty 5.0 of 10

    Selecting instruction-tuning samples by the loss difference between text-only and multimodal prediction (VisNec) lets a model match or exceed full-data performance with only 15% of the data.

  7. Streamlining the Development of Active Learning Methods in Real-World Object Detection

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A crop-based similarity metric called OSS predicts which active-learning strategies will work for object detection and picks stable validation subsets before expensive training runs.

  8. Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    A budget-aware framework (PU-ADKA) selects which domain expert an LLM should query under a fixed $100 budget, improving specialized-domain answers at low cost.

  9. To Label or Not to Label: PALM -- A Predictive Model for Evaluating Sample Efficiency in Active Learning Models

    cs.LG 2025-07 conditional novelty 5.0 of 10

    PALM fits a four-parameter saturation curve to early active learning accuracy data and extrapolates it to predict the full learning trajectory.

  10. Cost-effective Reduced-Order Modeling via Bayesian Active Learning

    cs.LG 2025-06 conditional novelty 4.0 of 10

    An active learning framework for reduced-order models, BayPOD-AL, shows that an error-bounded acquisition function outperforms uncertainty sampling and random sampling on a 1D heat equation surrogate task.

Pith tools