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

2026-04-22

AI Summary

This work addresses the challenge of sample selection in low-resource, highly class-imbalanced clinical settings, where conventional methods are prone to outlier interference, degrading transfer learning performance. To overcome this limitation, the authors propose RADS, a novel approach that, for the first time, integrates reinforcement learning into this task. RADS adaptively selects high-quality samples for fine-tuning by jointly optimizing their informativeness and representativeness. The method combines uncertainty-based and diversity-aware sampling mechanisms, enabling robust and effective sample selection. Evaluated on multiple real-world clinical datasets, RADS consistently outperforms existing approaches, significantly enhancing model transferability while maintaining strong robustness against data imbalance and noise.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

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.

Problem

• transfer learning
• low-resource
• class imbalance
• sample selection
• clinical settings

Innovation

• Reinforcement Learning
• Sample Selection
• Transfer Learning
• Class Imbalance
• Clinical Data