Graph Neural Networks Powered by Encoder Embedding for Improved Node Learning

TL;DR

This paper introduces a structure-aware initialization method for graph neural networks using encoder embeddings, significantly enhancing their training stability and accuracy in node classification tasks.

Contribution

It proposes a novel, statistically grounded encoder embedding for GNN initialization, leading to improved performance and stability across various benchmarks.

Findings

GEE improves GNN convergence and stability.

GG-C outperforms existing methods by 10-50% accuracy.

Structure-aware initialization enhances graph topology exploitation.

Abstract

Graph neural networks (GNNs) have emerged as a powerful framework for a wide range of node-level graph learning tasks. However, their performance typically depends on random or minimally informed initial feature representations, where poor initialization can lead to slower convergence and increased training instability. In this paper, we address this limitation by leveraging a statistically grounded one-hot graph encoder embedding (GEE) as a high-quality, structure-aware initialization for node features. Integrating GEE into standard GNNs yields the GEE-powered GNN (GG) framework. Across extensive simulations and real-world benchmarks, GG provides consistent and substantial performance gains in both unsupervised and supervised settings. For node classification, we further introduce GG-C, which concatenates the outputs of GG and GEE and outperforms competing methods, achieving roughly 10-50% accuracy improvements across most datasets. These results demonstrate the importance of principled, structure-aware initialization for improving the efficiency, stability, and overall performance of graph neural network architecture, enabling models to better exploit graph topology from the outset.