mlsanityData to 14 Oct 2026

Dependency-aware Maximum Likelihood Estimation for Active Learning

arXiv 2503.05969 ↗First posted 7 Mar 2025cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Active learning aims to efficiently build a labeled training set by strategically selecting samples to query labels from annotators. In this sequential process, each sample acquisition influences subsequent selections, causing dependencies among samples in the labeled set. However, these dependencies are overlooked during the model parameter estimation stage when updating the model using Maximum Likelihood Estimation (MLE), a conventional method that assumes independent and identically distributed (i.i.d.) data. We propose Dependency-aware MLE (DMLE), which corrects MLE within the active learning framework by addressing sample dependencies typically neglected due to the i.i.d. assumption, ensuring consistency with active learning principles in the model parameter estimation process. This improved method achieves superior performance across multiple benchmark datasets, reaching higher performance in earlier cycles compared to conventional MLE. Specifically, we observe average accuracy improvements of 6%, 8.6%, and 10.5% for k=1, k=5, and k=10 respectively, after collecting the first 100 samples, where entropy is the acquisition function and k is the query batch size acquired at every active learning cycle. Our implementation is publicly available at: https://github.com/neu-spiral/DMLEforAL

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 72 references that are in the map. First posted on arXiv 7 Mar 2025.

Builds on

25 of 72 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2017Deep Bayesian Active Learning with Image Datacited by 819
  5. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  6. 2020A Survey of Deep Active Learningcited by 554
  7. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  8. 2018A Survey on Deep Transfer Learningcited by 419
  9. 2019A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysiscited by 151
  10. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  11. 2021Batch Active Learning at Scalecited by 127
  12. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 93
13 more
  1. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  2. 2021On Statistical Bias In Active Learning: How and When To Fix Itcited by 75
  3. 2020A Close Look at Deep Learning with Small Datacited by 54
  4. 2019Batch Active Learning Using Determinantal Point Processescited by 43
  5. 2019Sampling Bias in Deep Active Classification: An Empirical Studycited by 36
  6. 2020Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervisioncited by 32
  7. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  8. 2022Making Your First Choice: To Address Cold Start Problem in Vision Active Learningcited by 25
  9. 2018MedAL: Deep Active Learning Sampling Method for Medical Image Analysiscited by 20
  10. 2016Asymptotic Analysis of Objectives based on Fisher Information in Active Learningcited by 14
  11. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  12. 2021Mitigating Sampling Bias and Improving Robustness in Active Learningcited by 5
  13. 2021Probabilistic Active Learning for Active Class Selectioncited by 2

Built on by

Not cited yet.