arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08986cs.LGcs.AI
收藏

改进分层多标签学习中稀有节点的检测

Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning

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)

Isaac Xu, Martin Gillis, Ayushi Sharma, Benjamin Misiuk, Craig J. Brown, Thomas Trappenberg

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。

摘要:

在分层多标签分类中,一个持续的挑战是使模型预测能够达到层次结构的更深层次,以实现更详细或更细粒度的分类。这一困难部分源于某些类别(或层次节点)的自然稀有性,以及确保子节点几乎总是比其父节点频率更低的分层约束。为了解决这个问题,我们为神经网络提出了一种加权损失目标,该目标结合了节点不平衡加权和焦点加权组件,后者利用了集成不确定性的现代量化。通过强调稀有节点而非稀有观测(数据点),并在训练过程中关注每个模型输出分布中的不确定节点,我们观察到在基准数据集上召回率提高了高达五倍,并且$F_{1}$分数有统计显著的提升。我们还展示了我们的方法有助于卷积网络处理具有挑战性的任务,例如在编码器次优或数据有限的情况下。

英文摘要:

In hierarchical multi-label classification, a persistent challenge is enabling model predictions to reach deeper levels of the hierarchy for more detailed or fine-grained classifications. This difficulty partly arises from the natural rarity of certain classes (or hierarchical nodes) and the hierarchical constraint that ensures child nodes are almost always less frequent than their parents. To address this, we propose a weighted loss objective for neural networks that combines node-wise imbalance weighting with focal weighting components, the latter leveraging modern quantification of ensemble uncertainties. By emphasizing rare nodes rather than rare observations (data points), and focusing on uncertain nodes for each model output distribution during training, we observe improvements in recall by up to a factor of five on benchmark datasets, along with statistically significant gains in $F_{1}$ score. We also show our approach aids convolutional networks on challenging tasks, as in situations with suboptimal encoders or limited data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑