arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.05860cs.AI
收藏

GNN-XML:用于极端多标签文本分类的图神经网络

GNN-XML: Graph Neural Networks for Extreme Multi-label Text Classification

East China Normal University(华东师范大学)

Daoming Zong, Shiliang Sun

摘要:

极端多标签文本分类(XMTC)的目标是从一个非常大的标签集标记一个文本实例与最相关的标签子集。XMTC在新闻标注、产品推荐等现代应用中产生了大量的标签集,引起了人们的广泛关注。XMTC的主要挑战是数据的可扩展性和稀疏性,从而导致两个问题:i)难以扩展到极端标签设置,ii)存在长尾标签分布,这意味着大部分标签几乎没有正训练实例。为了克服这些问题,我们提出了GNN-XML,一个可扩展的图神经网络框架XMTC问题量身定制。具体来说,我们利用标签的相关性,通过挖掘他们的共现模式,并建立一个标签图的相关矩阵的基础上。然后,我们进行属性图聚类通过执行图卷积与低通图过滤器,以联合模型的标签依赖和标签功能,从而导致语义标签集群。我们进一步提出了一个双边分支图同构网络来解耦表示学习和分类器学习,以更好地建模尾部标签。在多个基准数据集上的实验结果表明,GNN-XML显著优于最先进的方法,同时保持了相当的预测效率和模型大小。

英文摘要:

Extreme multi-label text classification (XMTC) aims to tag a text instance with the most relevant subset of labels from an extremely large label set. XMTC has attracted much recent attention due to massive label sets yielded by modern applications, such as news annotation and product recommendation. The main challenges of XMTC are the data scalability and sparsity, thereby leading to two issues: i) the intractability to scale to the extreme label setting, ii) the presence of long-tailed label distribution, implying that a large fraction of labels have few positive training instances. To overcome these problems, we propose GNN-XML, a scalable graph neural network framework tailored for XMTC problems. Specifically, we exploit label correlations via mining their co-occurrence patterns and build a label graph based on the correlation matrix. We then conduct the attributed graph clustering by performing graph convolution with a low-pass graph filter to jointly model label dependencies and label features, which induces semantic label clusters. We further propose a bilateral-branch graph isomorphism network to decouple representation learning and classifier learning for better modeling tail labels. Experimental results on multiple benchmark datasets show that GNN-XML significantly outperforms state-of-the-art methods while maintaining comparable prediction efficiency and model size.

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。

↑