arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.08159cs.LG
收藏

在文本丰富网络中学习层次化知识:基于分类学的表示学习

Learning Hierarchical Knowledge in Text-Rich Networks with Taxonomy-Informed Representation Learning

State Key Laboratory for Novel Software Technology(新型软件技术国家重点实验室);Nanjing University(南京大学);Ant Group(蚂蚁集团)

Yunhui Liu, Yongchao Liu, Yinfeng Chen, Chuntao Hong, Tao Zheng, Tieke He

AI总结:

TIER通过构建隐含层次分类学并整合到节点表示中,提升文本丰富网络的层次化知识学习能力,实现更可解释的结构化建模。

摘要:

层次化知识结构在现实世界中普遍存在,并在从粗到细的语义层次上组织信息起着至关重要的作用。尽管此类结构已被广泛应用于分类系统、生物医学本体和检索增强生成,但其在文本丰富网络(TRNs)中的潜力仍被低估,其中每个节点包含丰富的文本内容,边编码语义关系。现有方法在学习TRNs时往往专注于扁平语义建模,忽略了文本文档中固有的层次化语义。为此,我们提出了TIER(在文本丰富网络上基于分类学的层次化表示学习),首先构建一个隐含的层次化分类学,然后将其整合到学习的节点表示中。具体来说,TIER采用相似性引导的对比学习构建一个聚类友好的嵌入空间,随后进行层次化K均值聚类,再通过大语言模型进行聚类细化,以实现语义连贯的分类学构建。利用由此得到的分类学,TIER引入基于共现系数的正则化损失,以对齐学习的嵌入与层次结构。通过学习尊重细粒度和粗粒度语义的表示,TIER能够更可解释和结构化地建模现实中的TRNs。我们证明,我们的方法在多个跨不同领域的数据集上显著优于现有方法,突显了层次化知识学习对TRNs的重要性。

英文摘要:

Hierarchical knowledge structures are ubiquitous across real-world domains and play a vital role in organizing information from coarse to fine semantic levels. While such structures have been widely used in taxonomy systems, biomedical ontologies, and retrieval-augmented generation, their potential remains underexplored in the context of Text-Rich Networks (TRNs), where each node contains rich textual content and edges encode semantic relationships. Existing methods for learning on TRNs often focus on flat semantic modeling, overlooking the inherent hierarchical semantics embedded in textual documents. To this end, we propose TIER (Hierarchical \textbf{T}axonomy-\textbf{I}nformed R\textbf{E}presentation Learning on Text-\textbf{R}ich Networks), which first constructs an implicit hierarchical taxonomy and then integrates it into the learned node representations. Specifically, TIER employs similarity-guided contrastive learning to build a clustering-friendly embedding space, upon which it performs hierarchical K-Means followed by LLM-powered clustering refinement to enable semantically coherent taxonomy construction. Leveraging the resulting taxonomy, TIER introduces a cophenetic correlation coefficient-based regularization loss to align the learned embeddings with the hierarchical structure. By learning representations that respect both fine-grained and coarse-grained semantics, TIER enables more interpretable and structured modeling of real-world TRNs. We demonstrate that our approach significantly outperforms existing methods on multiple datasets across diverse domains, highlighting the importance of hierarchical knowledge learning for TRNs.

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。

↑