一种结合回归和分类任务进行联合特征选择的多任务学习方法
A multi-task learning approach combining regression and classification tasks for joint feature selection.
摘要(中文译文)
多任务学习（MTL）是一种能够同时训练多个相互通信算法的学习范式，已广泛应用于生物医学分析中以识别共享生物标志物。尽管多任务学习已成功支持回归或分类任务，但将混合类型的任务整合到一个统一的多任务学习框架中仍然具有挑战性，尤其是在生物医学领域，这可能导致有偏倚的生物标志物识别。为解决这一问题，我们提出了一种改进的多任务学习方法MTLComb，该方法通过平衡回归与分类任务的权重来促进无偏倚的生物标志物识别。我们通过对模拟数据以及涉及脓毒症和精神分裂症的实际生物医学研究进行分析，证明了MTLComb的算法效率和临床实用性。代码可在https://github.com/transbioZI/MTLComb获取。
Abstract
Multi-task learning (MTL) is a learning paradigm that enables the simultaneous training of multiple communicating algorithms, and has been widely applied in the biomedical analysis for shared biomarker identification. Although MTL has successfully supported either regression or classification tasks, incorporating mixed types of tasks into a unified MTL framework remains challenging, especially in biomedicine, where it can lead to biased biomarker identification. To address this issue, we propose an improved method of multi-task learning, MTLComb, which balances the weights of regression and classification tasks to promote unbiased biomarker identification. We demonstrate the algorithmic efficiency and clinical utility of MTLComb through analyses on both simulated data and actual biomedical studies pertaining to sepsis and schizophrenia. The code is available at https://github.com/transbioZI/MTLComb .
如何引用
AMA
Han Cao, Sivanesan Rajan, Bianka Hahn, Ersoy Kocak, Manuel Brenner, Florian Hess, et al. A multi-task learning approach combining regression and classification tasks for joint feature selection.. Scientific reports. 2026; doi:10.1038/s41598-026-43551-3.
APA
Han Cao, Sivanesan Rajan, Bianka Hahn, Ersoy Kocak, Manuel Brenner, Florian Hess, et al (2026). A multi-task learning approach combining regression and classification tasks for joint feature selection.. Scientific reports. https://doi.org/10.1038/s41598-026-43551-3
GB/T 7714
Han Cao, Sivanesan Rajan, Bianka Hahn, Ersoy Kocak, Manuel Brenner, Florian Hess, et al. A multi-task learning approach combining regression and classification tasks for joint feature selection.[J]. Scientific reports, 2026 doi:10.1038/s41598-026-43551-3.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出