解决极端分类中稀有类别分类不准的问题
Optimizing Classification of Infrequent Labels by Reducing Variability in Label Distribution
- 采用孪生网络结构迁移知识，降低标签不一致
- 在多个数据集上显著提升稀有类别的分类性能
- 适合做极端分类与多意图识别的研究者
本文提出一种新方法 LEVER，应对极端分类（XC）任务中稀有类别表现不佳的问题。稀有类别通常样本稀疏，导致标签不一致，影响分类效果。LEVER 通过鲁棒的孪生网络架构，利用知识迁移减少标签不一致，提升 One-vs-All 分类器性能。在多个 XC 数据集上的全面测试显示，该方法在处理稀有类别时取得显著改进，树立了新基准。此外，论文还构建了两个新的多意图数据集，为未来 XC 研究提供重要资源。
原文摘要 · Abstract (English)
This paper presents a novel solution, LEVER, designed to address the challenges posed by underperforming infrequent categories in Extreme Classification (XC) tasks. Infrequent categories, often characterized by sparse samples, suffer from high label inconsistency, which undermines classification performance. LEVER mitigates this problem by adopting a robust Siamese-style architecture, leveraging knowledge transfer to reduce label inconsistency and enhance the performance of One-vs-All classifiers. Comprehensive testing across multiple XC datasets reveals substantial improvements in the handling of infrequent categories, setting a new benchmark for the field. Additionally, the paper introduces two newly created multi-intent datasets, offering essential resources for future XC research.
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。