Fine-grained graph representation learning for heterogeneous mobile networks with attentive fusion and contrastive learning

TL;DR

This paper introduces an unsupervised framework for automatically refining and updating wireless data knowledge graphs in mobile networks, leveraging graph structure learning, network stratification, and recurrent neural networks to improve node classification accuracy.

Contribution

The paper proposes a novel unsupervised data-and-model driven graph structure learning framework tailored for dynamic, heterogeneous mobile network data, enhancing knowledge graph construction and maintenance.

Findings

DMGSL outperforms baselines in node classification accuracy

Effective stratification improves heterogeneity handling

Incorporating historical data enhances dynamic graph modeling

Abstract

AI becomes increasingly vital for telecom industry, as the burgeoning complexity of upcoming mobile communication networks places immense pressure on network operators. While there is a growing consensus that intelligent network self-driving holds the key, it heavily relies on expert experience and knowledge extracted from network data. In an effort to facilitate convenient analytics and utilization of wireless big data, we introduce the concept of knowledge graphs into the field of mobile networks, giving rise to what we term as wireless data knowledge graphs (WDKGs). However, the heterogeneous and dynamic nature of communication networks renders manual WDKG construction both prohibitively costly and error-prone, presenting a fundamental challenge. In this context, we propose an unsupervised data-and-model driven graph structure learning (DMGSL) framework, aimed at automating WDKG refinement and updating. Tackling WDKG heterogeneity involves stratifying the network into homogeneous layers and refining it at a finer granularity. Furthermore, to capture WDKG dynamics effectively, we segment the network into static snapshots based on the coherence time and harness the power of recurrent neural networks to incorporate historical information. Extensive experiments conducted on the established WDKG demonstrate the superiority of the DMGSL over the baselines, particularly in terms of node classification accuracy.