Representation Learning for Attributed Multiplex Heterogeneous Network

TLDR

Network embedding is widely used, yet existing methods focus on single‑typed nodes/edges and struggle to scale to large, multi‑typed, attributed networks. This work formalizes embedding learning for attributed multiplex heterogeneous networks and proposes a unified framework to address it. The framework supports transductive and inductive learning, is theoretically grounded, and is evaluated on Amazon, YouTube, Twitter, and Alibaba datasets. Experiments show 5.99–28.23% F1 lift over state‑of‑the‑art link‑prediction baselines, and the framework was successfully deployed in Alibaba’s recommendation system, where offline A/B tests confirm its practical effectiveness and efficiency.

Abstract

Network embedding (or graph embedding) has been widely used in many real-world applications. However, existing methods mainly focus on networks with single-typed nodes/edges and cannot scale well to handle large networks. Many real-world networks consist of billions of nodes and edges of multiple types, and each node is associated with different attributes. In this paper, we formalize the problem of embedding learning for the Attributed Multiplex Heterogeneous Network and propose a unified framework to address this problem. The framework supports both transductive and inductive learning. We also give the theoretical analysis of the proposed framework, showing its connection with previous works and proving its better expressiveness. We conduct systematical evaluations for the proposed framework on four different genres of challenging datasets: Amazon, YouTube, Twitter, and Alibaba. Experimental results demonstrate that with the learned embeddings from the proposed framework, we can achieve statistically significant improvements (e.g., 5.99-28.23% lift by F1 scores; p<<0.01, t-test) over previous state-of-the-art methods for link prediction. The framework has also been successfully deployed on the recommendation system of a worldwide leading e-commerce company, Alibaba Group. Results of the offline A/B tests on product recommendation further confirm the effectiveness and efficiency of the framework in practice.