Pith. sign in

REVIEW 10 cited by

Adversarial Active Learning for Deep Networks: a Margin Based Approach

Not yet reviewed by Pith; the record is open.

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 1802.09841 v1 pith:VR3BKATR submitted 2018-02-27 cs.LG cs.CVstat.ML

Adversarial Active Learning for Deep Networks: a Margin Based Approach

classification cs.LG cs.CVstat.ML
keywords activelearningadversarialdecisiondeepexamplesnetworksboundaries
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose a new active learning strategy designed for deep neural networks. The goal is to minimize the number of data annotation queried from an oracle during training. Previous active learning strategies scalable for deep networks were mostly based on uncertain sample selection. In this work, we focus on examples lying close to the decision boundary. Based on theoretical works on margin theory for active learning, we know that such examples may help to considerably decrease the number of annotations. While measuring the exact distance to the decision boundaries is intractable, we propose to rely on adversarial examples. We do not consider anymore them as a threat instead we exploit the information they provide on the distribution of the input space in order to approximate the distance to decision boundaries. We demonstrate empirically that adversarial active queries yield faster convergence of CNNs trained on MNIST, the Shoe-Bag and the Quick-Draw datasets.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

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

  1. Test Case Selection for Deep Neural Networks: A Replication Study on LLMs for Code

    cs.SE 2026-06 unverdicted novelty 6.0

    Replication of TCS strategies on 17 LLM instances across three code tasks shows only partial generalization from vision DNN results, with uncertainty features aiding early failure discovery and representation features...

  2. Multimodal Distribution Matching for Vision-Language Dataset Distillation

    cs.CV 2026-05 unverdicted novelty 6.0

    MDM distills vision-language datasets via joint embedding clustering, weight-space model interpolation, and geometry-aware distribution matching on the unit hypersphere.

  3. ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying

    cs.CR 2026-04 unverdicted novelty 6.0

    ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.

  4. Discriminative Active Learning

    cs.LG 2019-07 unverdicted novelty 6.0

    DAL poses batch active learning as a binary classification task between labeled and unlabeled data to select informative examples for labeling.

  5. Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency

    cs.LG 2026-06 unverdicted novelty 5.0

    Deep active re-labeling allocates annotation budget to re-annotate noisy instances detected via active noise sampling, yielding more data-efficient and noise-resilient results than standard DAL.

  6. OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework

    cs.LG 2026-06 unverdicted novelty 5.0

    OrderDP is a plug-and-play data pruning method that selects a random subset then top-q samples to guarantee unbiased surrogate-loss training with convergence analysis and over 40% training cost reduction on CIFAR and ...

  7. Revisiting Active Sequential Prediction-Powered Mean Estimation

    stat.ML 2026-04 unverdicted novelty 5.0

    Non-asymptotic analysis of prediction-powered mean estimation shows that no-regret learning for query probabilities converges to the maximum allowed constant value, independent of covariates.

  8. ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation

    cs.IR 2026-04 unverdicted novelty 5.0

    ALDEN boosts private data extraction rates from RAG systems by combining active learning for query diversification with dynamic estimation of the underlying knowledge-base topic distribution.

  9. RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning

    cs.LG 2026-06 unverdicted novelty 4.0

    RCAP introduces class-aware probabilistic pruning that uses closed-form per-class fractions updated by loss and high-loss sampling to preserve worst-group accuracy at high pruning rates.

  10. Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance

    cs.LG 2026-05 unverdicted novelty 4.0

    Active learning with foundation model priors achieves over 50% annotation savings on imbalanced noisy datasets across image and text domains while maintaining performance.