Meta-Graph Based HIN Spectral Embedding: Methods, Analyses, and Insights

TL;DR

This paper introduces a novel framework for HIN spectral embedding using meta-graphs, combining empirical analysis and an autoencoder-based method to improve embedding quality and interpretability.

Contribution

It provides the first comprehensive theoretical and empirical analysis of meta-graph utility and proposes an end-to-end unsupervised method for combining multiple meta-graphs in HIN embedding.

Findings

Meta-graph assessment effectively evaluates embedding quality.

The autoencoder method captures multi-dimensional semantics.

The framework outperforms state-of-the-art neural embedding methods.

Abstract

In this work, we propose to study the utility of different meta-graphs, as well as how to simultaneously leverage multiple meta-graphs for HIN embedding in an unsupervised manner. Motivated by prolific research on homogeneous networks, especially spectral graph theory, we firstly conduct a systematic empirical study on the spectrum and embedding quality of different meta-graphs on multiple HINs, which leads to an efficient method of meta-graph assessment. It also helps us to gain valuable insight into the higher-order organization of HINs and indicates a practical way of selecting useful embedding dimensions. Further, we explore the challenges of combining multiple meta-graphs to capture the multi-dimensional semantics in HIN through reasoning from mathematical geometry and arrive at an embedding compression method of autoencoder with $\ell_{2,1}$-loss, which finds the most informative meta-graphs and embeddings in an end-to-end unsupervised manner. Finally, empirical analysis suggests a unified workflow to close the gap between our meta-graph assessment and combination methods. To the best of our knowledge, this is the first research effort to provide rich theoretical and empirical analyses on the utility of meta-graphs and their combinations, especially regarding HIN embedding. Extensive experimental comparisons with various state-of-the-art neural network based embedding methods on multiple real-world HINs demonstrate the effectiveness and efficiency of our framework in finding useful meta-graphs and generating high-quality HIN embeddings.