mlsanityData to 14 Oct 2026

RADS: Reinforcement Learning-Based Sample Selection Improves Transfer Learning in Low-resource and Imbalanced Clinical Settings

arXiv 2604.20256 ↗First posted 22 Apr 2026cs.CL cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

A common strategy in transfer learning is few shot fine-tuning, but its success is highly dependent on the quality of samples selected as training examples. Active learning methods such as uncertainty sampling and diversity sampling can select useful samples. However, under extremely low-resource and class-imbalanced conditions, they often favor outliers rather than truly informative samples, resulting in degraded performance. In this paper, we introduce RADS (Reinforcement Adaptive Domain Sampling), a robust sample selection strategy using reinforcement learning (RL) to identify the most informative samples. Experimental evaluations on several real world clinical datasets show our sample selection strategy enhances model transferability while maintaining robust performance under extreme class imbalance compared to traditional methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 16 of its 41 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

16 of 41 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  4. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  5. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  6. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  7. 2019ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmissioncited by 493
  8. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  9. 2018A Survey on Deep Transfer Learningcited by 419
  10. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  11. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  12. 2021Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluationcited by 70
4 more
  1. 2020A Survey on Transfer Learning in Natural Language Processingcited by 33
  2. 2024TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Datacited by 30
  3. 2024Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Processcited by 9
  4. 2023A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcarecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domain
  2. 2024Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review
  3. 2024On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling, and Beyond
  4. 2025Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
  5. 2025RELEAP: Reinforcement-Enhanced Label-Efficient Active Phenotyping for Electronic Health Records
  6. 2026The hidden risks of temporal resampling in clinical reinforcement learning
  7. 2025Statistical and Algorithmic Foundations of Reinforcement Learning
  8. 2024BOTS: Batch Bayesian Optimization of Extended Thompson Sampling for Severely Episode-Limited RL Settings