mlsanityData to 7 Oct 2026

Neural Active Learning Beyond Bandits

arXiv 2404.12522 ↗First posted 18 Apr 2024cs.LG cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

We study both stream-based and pool-based active learning with neural network approximations. A recent line of works proposed bandit-based approaches that transformed active learning into a bandit problem, achieving both theoretical and empirical success. However, the performance and computational costs of these methods may be susceptible to the number of classes, denoted as K, due to this transformation. Therefore, this paper seeks to answer the question: "How can we mitigate the adverse impacts of K while retaining the advantages of principled exploration and provable performance guarantees in active learning?" To tackle this challenge, we propose two algorithms based on the newly designed exploitation and exploration neural networks for stream-based and pool-based active learning. Subsequently, we provide theoretical performance guarantees for both algorithms in a non-parametric setting, demonstrating a slower error-growth rate concerning K for the proposed approaches. We use extensive experiments to evaluate the proposed algorithms, which consistently outperform state-of-the-art baselines.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 37 of its 69 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

37 of 69 references.

References · 37

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  3. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 784
  4. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  5. 2019On Exact Computation with an Infinitely Wide Neural Netcited by 572
  6. 2020A Survey of Deep Active Learningcited by 547
  7. 2019Learning Loss for Active Learningcited by 335
  8. 2019Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networkscited by 221
  9. 2020Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oraclescited by 195
  10. 2021Batch Active Learning at Scalecited by 127
  11. 2020Confidence-Aware Learning for Deep Neural Networkscited by 113
  12. 2019Diverse mini-batch Active Learningcited by 88
25 more
  1. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  2. 2021Influence Selection for Active Learningcited by 82
  3. 2020Model Selection in Contextual Stochastic Bandit Problemscited by 71
  4. 2016Learning to Decode Linear Codes Using Deep Learningcited by 60
  5. 2021EE-Net: Exploitation-Exploration Neural Networks in Contextual Banditscited by 43
  6. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  7. 2020Efficient active learning of sparse halfspaces with arbitrary bounded noisecited by 29
  8. 2021Local Clustering in Contextual Multi-Armed Banditscited by 29
  9. 2021Neural Active Learning with Performance Guaranteescited by 22
  10. 2021Diversity Enhanced Active Learning with Strictly Proper Scoring Rulescited by 22
  11. 2019Exploring Representativeness and Informativeness for Active Learningcited by 21
  12. 2018Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensemblescited by 20
  13. 2021Multi-facet Contextual Bandits: A Neural Network Perspectivecited by 20
  14. 2023Graph Neural Banditscited by 20
  15. 2021Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noisecited by 18
  16. 2022Comprehensive Fair Meta-learned Recommender Systemcited by 18
  17. 2020Generic Outlier Detection in Multi-Armed Banditcited by 14
  18. 2018Efficient active learning of sparse halfspacescited by 13
  19. 2022Active Learning with Neural Networks: Insights from Nonparametric Statisticscited by 13
  20. 2017Adaptivity to Noise Parameters in Nonparametric Active Learningcited by 12
  21. 2022Improved Algorithms for Neural Active Learningcited by 11
  22. 2016Active Nearest-Neighbor Learning in Metric Spacescited by 9
  23. 2022Neural Collaborative Filtering Bandits via Meta Learningcited by 7
  24. 2023Training-Free Neural Active Learning with Initialization-Robustness Guaranteescited by 5
  25. 2023Conversational Question Answering with Reformulations over Knowledge Graphcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 2.

10 papers.

  1. 2025Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuningcited by 21
  2. 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimizationcited by 16
  3. 2024PageRank Bandits for Link Predictioncited by 14
  4. 2026Real-Time Aligned Reward Model beyond Semanticscited by 12
  5. 2024Meta Clustering of Neural Banditscited by 7
  6. 2025DRMD: Deep Reinforcement Learning for Malware Detection under Concept Driftcited by 7
  7. 2025Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Enginescited by 3
  8. 2024Neural Active Learning Meets the Partial Monitoring Frameworkcited by 1
  9. 2025Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticitycited by 1
  10. 2026Federated Reasoning Distillation Framework with Model Learnability-Aware Data Allocationcited by 0