mlsanityData to 7 Oct 2026

Semi-supervised Batch Active Learning via Bilevel Optimization

arXiv 2010.09654 ↗First posted 19 Oct 2020cs.LG cs.SD stat.MLcited by 16

Not on the map. Why?

Abstract (arXiv)

Active learning is an effective technique for reducing the labeling cost by improving data efficiency. In this work, we propose a novel batch acquisition strategy for active learning in the setting where the model training is performed in a semi-supervised manner. We formulate our approach as a data summarization problem via bilevel optimization, where the queried batch consists of the points that best summarize the unlabeled data pool. We show that our method is highly effective in keyword detection tasks in the regime when only few labeled samples are available.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 7; 2023: 4; 2024: 3.

16 papers.

Sort:

By area:

  1. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  2. 2022DeepCore: A Comprehensive Library for Coreset Selection in Deep Learningcited by 146
  3. 2022A Framework and Benchmark for Deep Batch Active Learning for Regressioncited by 47
  4. 2024AIDE: An Automatic Data Engine for Object Detection in Autonomous Drivingcited by 26
  5. 2022Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernelscited by 25
  6. 2023LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learningcited by 20
  7. 2022On Sampling Collaborative Filtering Datasetscited by 8
  8. 2021Data Summarization via Bilevel Optimizationcited by 7
  9. 2022Consistency-Based Semi-supervised Evidential Active Learning for Diagnostic Radiograph Classificationcited by 7
  10. 2024Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classificationcited by 7
  11. 2022Neural Active Learning on Heteroskedastic Distributionscited by 5
  12. 2022Black-box Coreset Variational Inferencecited by 4
4 more
  1. 2024Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applicationscited by 4
  2. 2023NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coveragecited by 3
  3. 2023Farzi Data: Autoregressive Data Distillationcited by 3
  4. 2023Learning to Rank for Active Learning via Multi-Task Bilevel Optimizationcited by 3