跳到主要导航 跳到搜索 跳到主要内容

Mastering the Minority: An Uncertainty-Guided Multi-Expert Framework for Challenging-Tailed Sequence Learning

  • Ye Wang
  • , Zixuan Wu
  • , Lifeng Shen
  • , Jiang Xie
  • , Xiaoling Wang
  • , Hong Yu*
  • , Guoyin Wang
  • *此作品的通讯作者
  • Chongqing University of Posts and Telecommunications
  • Chongqing Normal University

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Imbalanced data distribution remains a critical challenge in sequential learning, leading models to easily recognize frequent categories while failing to detect minority classes adequately. The Mixture-of-Experts model offers a scalable solution, yet its application is often hindered by parameter inefficiency, poor expert specialization, and difficulty in resolving prediction conflicts. To Master the Minority classes effectively, we propose the Uncertainty-based Multi-Expert fusion network (UME) framework. UME is designed with three core innovations: First, we employ Ensemble LoRA for parameter-efficient modeling, significantly reducing the trainable parameter count. Second, we introduce Sequential Specialization guided by Dempster-Shafer Theory (DST), which ensures effective specialization on the challenging-tailed classes. Finally, an Uncertainty-Guided Fusion mechanism uses DST's certainty measures to dynamically weigh expert opinions, resolving conflicts by prioritizing the most confident expert for reliable final predictions. Extensive experiments across four public hierarchical text classification datasets demonstrate that UME achieves state-of-the-art performance. We achieve a performance gain of up to 17.97% over the best baseline on individual categories, while reducing trainable parameters by up to 10.32%. The findings highlight that uncertainty-guided expert coordination is a principled strategy for addressing challenging-tailed sequence learning.

源语言英语
页(从-至)1802-1814
页数13
期刊IEEE Transactions on Audio, Speech and Language Processing
卷34
DOI
出版状态已出版 - 2026

学术指纹

探究 'Mastering the Minority: An Uncertainty-Guided Multi-Expert Framework for Challenging-Tailed Sequence Learning' 的科研主题。它们共同构成独一无二的学术指纹。

引用此