mlsanityData to 14 Oct 2026

ORIS: Online Active Learning Using Reinforcement Learning-based Inclusive Sampling for Robust Streaming Analytics System

arXiv 2411.18060 ↗First posted 27 Nov 2024cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Effective labeled data collection plays a critical role in developing and fine-tuning robust streaming analytics systems. However, continuously labeling documents to filter relevant information poses significant challenges like limited labeling budget or lack of high-quality labels. There is a need for efficient human-in-the-loop machine learning (HITL-ML) design to improve streaming analytics systems. One particular HITL- ML approach is online active learning, which involves iteratively selecting a small set of the most informative documents for labeling to enhance the ML model performance. The performance of such algorithms can get affected due to human errors in labeling. To address these challenges, we propose ORIS, a method to perform Online active learning using Reinforcement learning-based Inclusive Sampling of documents for labeling. ORIS aims to create a novel Deep Q-Network-based strategy to sample incoming documents that minimize human errors in labeling and enhance the ML model performance. We evaluate the ORIS method on emotion recognition tasks, and it outperforms traditional baselines in terms of both human labeling performance and the ML model performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 35 references that are in the map. First posted on arXiv 27 Nov 2024.

Builds on

14 of 35 references.

References · 14

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  3. 2020A Survey of Deep Active Learningcited by 554
  4. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 486
  5. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 166
  6. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  7. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  8. 2018Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterioncited by 70
  9. 2021Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristicscited by 67
  10. 2020Reinforced active learning for image segmentationcited by 56
  11. 2020Modeling and mitigating human annotation errors to design efficient stream processing systems with human-in-the-loop machine learningcited by 21
  12. 2019Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approachcited by 8
2 more
  1. 2019Modeling Human Annotation Errors to Design Bias-Aware Systems for Social Stream Processingcited by 3
  2. 2013Engineering Crowdsourced Stream Processing Systemscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning
  2. 2026ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning
  3. 2026SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs
  4. 2024Dual Active Learning for Reinforcement Learning from Human Feedback
  5. 2024Image Classification with Deep Reinforcement Active Learning
  6. 2024Dataset Quantization with Active Learning based Adaptive Sampling
  7. 2025Efficient Process Reward Model Training via Active Learning
  8. 2025Active Advantage-Aligned Online Reinforcement Learning with Offline Data