mlsanityData to 7 Oct 2026

One-Round Active Learning

arXiv 2104.11843 ↗First posted 23 Apr 2021cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

In this work, we initiate the study of one-round active learning, which aims to select a subset of unlabeled data points that achieve the highest model performance after being labeled with only the information from initially labeled data points. The challenge of directly applying existing data selection criteria to the one-round setting is that they are not indicative of model performance when available labeled data is limited. We address the challenge by explicitly modeling the dependence of model performance on the dataset. Specifically, we propose DULO, a data-driven framework for one-round active learning, wherein we learn a model to predict the model performance for a given dataset and then leverage this model to guide the selection of unlabeled data. Our results demonstrate that DULO leads to the state-of-the-art performance on various active learning benchmarks in the one-round setting.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 11 of its 44 references that are in the map. First posted on arXiv 23 Apr 2021.

Builds on

11 of 44 references.

References · 11

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2017Deep Setscited by 1,394
  6. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  7. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  8. 2020GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learningcited by 224
  9. 2019Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithmscited by 147
  10. 2014Lazier Than Lazy Greedycited by 97
  11. 2013Optimal Bounds on Approximation of Submodular and XOS Functions by Juntascited by 6

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 1.

5 papers.

  1. 2022Retrieval-Augmented Generative Question Answering for Event Argument Extractioncited by 18
  2. 2021A Unified Framework for Task-Driven Data Quality Managementcited by 7
  3. 2022On Efficient Online Imitation Learning via Classificationcited by 5
  4. 2023Learning to Rank for Active Learning via Multi-Task Bilevel Optimizationcited by 3
  5. 2021Zero-Round Active Learningcited by 1