A Multi-Semantic Metapath Model for Large Scale Heterogeneous Network Representation Learning

TL;DR

This paper introduces a multi-semantic metapath model for large-scale heterogeneous network embedding, effectively handling unbalanced node and edge distributions in real-world data, and demonstrates improved link prediction performance.

Contribution

The paper proposes a novel multi-semantic metapath framework that constructs heterogeneous neighborhoods and improves large-scale network representation learning.

Findings

MSM achieves significant gains over previous methods on link prediction.

The model effectively manages unbalanced node and edge distributions.

Systematic evaluations on Amazon and Alibaba datasets validate its effectiveness.

Abstract

Network Embedding has been widely studied to model and manage data in a variety of real-world applications. However, most existing works focus on networks with single-typed nodes or edges, with limited consideration of unbalanced distributions of nodes and edges. In real-world applications, networks usually consist of billions of various types of nodes and edges with abundant attributes. To tackle these challenges, in this paper we propose a multi-semantic metapath (MSM) model for large scale heterogeneous representation learning. Specifically, we generate multi-semantic metapath-based random walks to construct the heterogeneous neighborhood to handle the unbalanced distributions and propose a unified framework for the embedding learning. We conduct systematical evaluations for the proposed framework on two challenging datasets: Amazon and Alibaba. The results empirically demonstrate that MSM can achieve relatively significant gains over previous state-of-arts on link prediction.