Link Prediction on Latent Heterogeneous Graphs

TL;DR

This paper introduces LHGNN, a novel method for link prediction on latent heterogeneous graphs where node and edge types are unobserved, by capturing latent semantics through semantic embeddings and personalized context modulation.

Contribution

The paper proposes LHGNN, a new model that effectively predicts links on latent heterogeneous graphs without relying on explicit type information, addressing a key challenge in HIN learning.

Findings

LHGNN outperforms existing methods on benchmark datasets.

Semantic and path-level embeddings effectively capture latent heterogeneity.

Personalized context modulation improves link prediction accuracy.

Abstract

On graph data, the multitude of node or edge types gives rise to heterogeneous information networks (HINs). To preserve the heterogeneous semantics on HINs, the rich node/edge types become a cornerstone of HIN representation learning. However, in real-world scenarios, type information is often noisy, missing or inaccessible. Assuming no type information is given, we define a so-called latent heterogeneous graph (LHG), which carries latent heterogeneous semantics as the node/edge types cannot be observed. In this paper, we study the challenging and unexplored problem of link prediction on an LHG. As existing approaches depend heavily on type-based information, they are suboptimal or even inapplicable on LHGs. To address the absence of type information, we propose a model named LHGNN, based on the novel idea of semantic embedding at node and path levels, to capture latent semantics on and between nodes. We further design a personalization function to modulate the heterogeneous contexts conditioned on their latent semantics w.r.t. the target node, to enable finer-grained aggregation. Finally, we conduct extensive experiments on four benchmark datasets, and demonstrate the superior performance of LHGNN.