Joint Embedding Of Meta-path And Meta-graph For Heterogeneous Information Networks

Abstract

Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks,where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph only considers the complex structural information, but ignores its embedded meta-paths information. To address this problem, we proposeMEta-GrAph-based network embedding models, called MEGA and MEGA++, respectively. The MEGA model uses normalized relevance or similarity measures that are derived from a meta-graph and its embedded meta-paths between nodes simultaneously, and then leverages tensor decomposition method to perform node embedding. The MEGA++ further facilitates the use of coupled tensor-matrix decomposition method to obtain a joint embedding for nodes, which simultaneously considers the hidden relations of all meta information of a meta-graph.Extensive experiments on two real datasets demonstrate thatMEGA and MEGA+

Stats

• citations25
• S2 citations—
• github stars0
• HF likes0
• heat score10.61
• arxiv keysun2018joint

Related papers

• Meta-path Guided Embedding For Similarity Search In Large-scale Heterogeneous Information Networks (2016)0.00
• Hetfs: A Method For Fast Similarity Search With Ad-hoc Meta-paths On Heterogeneous Information Networks (2025)4.52
• Unigraph2: Learning A Unified Embedding Space To Bind Multimodal Graphs (2025)6.77
• VERSE: Versatile Graph Embeddings From Similarity Measures (2018)17.42
• Document Network Embedding: Coping For Missing Content And Missing Links (2019)0.00
• Embedding Meta-textual Information For Improved Learning To Rank (2020)3.58
• Metaembed: Scaling Multimodal Retrieval At Test-time With Flexible Late Interaction (2025)2.35
• Hierarchical Graph Matching Network For Graph Similarity Computation (2020)0.00