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
Adversarial Active Learning for Deep Networks: a Margin Based Approach
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.
Forward citations
Cited by 10 Pith papers
-
Test Case Selection for Deep Neural Networks: A Replication Study on LLMs for Code
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...
-
Multimodal Distribution Matching for Vision-Language Dataset Distillation
MDM distills vision-language datasets via joint embedding clustering, weight-space model interpolation, and geometry-aware distribution matching on the unit hypersphere.
-
ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying
ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.
-
Discriminative Active Learning
DAL poses batch active learning as a binary classification task between labeled and unlabeled data to select informative examples for labeling.
-
Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency
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.
-
OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
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 ...
-
Revisiting Active Sequential Prediction-Powered Mean Estimation
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.
-
ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation
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.
-
RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning
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.
-
Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
Active learning with foundation model priors achieves over 50% annotation savings on imbalanced noisy datasets across image and text domains while maintaining performance.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.