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

2026-03-09

AI Summary

This work addresses the limitation of existing textual rich network (TRN) representation learning methods, which overlook the inherent hierarchical semantic structure in text and thus struggle to effectively model knowledge organization from coarse- to fine-grained levels. To overcome this, the authors propose TIER, a novel approach that introduces an implicit hierarchical taxonomy into TRNs for the first time. TIER jointly learns multi-level semantic representations through similarity-guided contrastive learning, hierarchical K-Means clustering, and a clustering strategy enhanced by large language models. Furthermore, it incorporates a regularization loss based on co-phenotype correlation coefficients to align the embedding space with the underlying hierarchy. Extensive experiments demonstrate that TIER significantly outperforms state-of-the-art methods across multiple cross-domain datasets, yielding representations with improved structural coherence, interpretability, and downstream task performance.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Machine Learning: Representation Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

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.

Problem

• Text-Rich Networks
• Hierarchical Knowledge
• Taxonomy
• Semantic Representation
• Node Embedding

Innovation

• Taxonomy-Informed Representation Learning
• Hierarchical Knowledge
• Text-Rich Networks
• Contrastive Learning
• Cophenetic Regularization