Refined Graph Encoder Embedding via Self-Training and Latent Community Recovery

TL;DR

This paper proposes a refined graph encoder embedding method that uses self-training and latent community recovery to improve vertex embeddings and community detection, supported by theoretical analysis and empirical validation.

Contribution

It introduces a novel refinement technique combining self-training and community recovery, with theoretical justification and demonstrated improvements in embedding quality and classification.

Findings

Enhanced ability to identify hidden communities

Improved vertex classification accuracy

Theoretical support for the refinement process

Abstract

This paper introduces a refined graph encoder embedding method, enhancing the original graph encoder embedding through linear transformation, self-training, and hidden community recovery within observed communities. We provide the theoretical rationale for the refinement procedure, demonstrating how and why our proposed method can effectively identify useful hidden communities under stochastic block models. Furthermore, we show how the refinement method leads to improved vertex embedding and better decision boundaries for subsequent vertex classification. The efficacy of our approach is validated through numerical experiments, which exhibit clear advantages in identifying meaningful latent communities and improved vertex classification across a collection of simulated and real-world graph data.