MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs

TL;DR

MetaHGNIE introduces a hypergraph contrastive learning framework leveraging meta-paths to effectively model high-order dependencies and align structural and semantic information for node importance estimation in heterogeneous knowledge graphs.

Contribution

It proposes a novel meta-path induced hypergraph contrastive learning approach that captures higher-order interactions and cross-modal signals in heterogeneous knowledge graphs.

Findings

Outperforms state-of-the-art NIE methods on benchmark datasets.

Effectively models high-order dependencies with meta-paths.

Enhances cross-modal alignment of structural and semantic features.

Abstract

Node importance estimation (NIE) in heterogeneous knowledge graphs is a critical yet challenging task, essential for applications such as recommendation, knowledge reasoning, and question answering. Existing methods often rely on pairwise connections, neglecting high-order dependencies among multiple entities and relations, and they treat structural and semantic signals independently, hindering effective cross-modal integration. To address these challenges, we propose MetaHGNIE, a meta-path induced hypergraph contrastive learning framework for disentangling and aligning structural and semantic information. MetaHGNIE constructs a higher-order knowledge graph via meta-path sequences, where typed hyperedges capture multi-entity relational contexts. Structural dependencies are aggregated with local attention, while semantic representations are encoded through a hypergraph transformer equipped with sparse chunking to reduce redundancy. Finally, a multimodal fusion module integrates structural and semantic embeddings under contrastive learning with auxiliary supervision, ensuring robust cross-modal alignment. Extensive experiments on benchmark NIE datasets demonstrate that MetaHGNIE consistently outperforms state-of-the-art baselines. These results highlight the effectiveness of explicitly modeling higher-order interactions and cross-modal alignment in heterogeneous knowledge graphs. Our code is available at https://github.com/SEU-WENJIA/DualHNIE