Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning
改进分层多标签学习中稀有节点的检测
机构 * Faculty of Computer Science(计算机科学学院) ; Dalhousie University(达尔豪斯大学) ; Department of Geography(地理系) ; Memorial University of Newfoundland(纽芬兰纪念大学) ; Department of Oceanography(海洋学系)
AI总结 针对分层多标签分类中稀有节点检测困难的问题,提出结合节点不平衡加权和焦点加权的损失函数,利用集成不确定性量化,在基准数据集上将召回率提升至五倍,并显著提高F1分数。
Comments Accepted for publication in Transactions on Machine Learning Research (TMLR), 2026