提出一种新型批量主动学习方法，提升大批次下的标注效率与性能。
Batch Bayesian Active Learning with Partial Batch Label Sampling
- 基于贝叶斯决策理论设计部分标签采样策略，解决大批量标注的计算瓶颈。
- 在多个数据集上实现固定预算下优于传统方法的准确率提升。
- 适合大规模预训练模型嵌入空间中的主动学习任务，尤其适用于资源受限场景。
近几十年来，众多主动学习选择函数被提出，令实践者难以抉择。基于贝叶斯的主动学习方法（如期望误差减少、期望预测信息增益、基于分歧的贝叶斯主动学习）具有可解释的优化目标。其关键挑战在于难以扩展至大批次，导致计算负担重（BatchBALD）或性能显著下降（top-$B$选择）。本文基于贝叶斯决策理论的一种特定形式，推导出针对EPIG算法的局部批量标签采样方法（ParBaLS）。实验表明，在多个数据集上，使用预训练模型嵌入的贝叶斯逻辑回归中，ParBaLS EPIG在固定预算下表现出更优性能。代码已开源：https://github.com/ADDAPT-ML/ParBaLS。
原文摘要 · Abstract (English)
Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice of which to use. Bayesian-based active learning offers principled objectives with explainable intuition, including Expected Error Reduction (EER), Expected Predictive Information Gain (EPIG), and Bayesian Active Learning by Disagreements (BALD). A key challenge of such methods is the difficult scaling to large batch sizes, leading to either computational challenges (BatchBALD) or dramatic performance drops (top-$B$ selection). Here, using a particular formulation of Bayesian Decision Theory, we derive Partial Batch Label Sampling (ParBaLS) for the EPIG algorithm. We show experimentally for several datasets that ParBaLS EPIG gives superior performance for a fixed budget and Bayesian Logistic Regression on embeddings from large pre-trained models. Our code is available at https://github.com/ADDAPT-ML/ParBaLS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。