SMGRL: Scalable Multi-resolution Graph Representation Learning

TL;DR

SMGRL introduces a scalable, multi-resolution framework for graph representation learning that efficiently captures both long- and short-range dependencies, improving classification accuracy on large graphs without high computational costs.

Contribution

It presents a model-agnostic, multi-resolution approach that reduces training costs by leveraging graph coarsening and self-similarity, enhancing GCN performance on large-scale graphs.

Findings

Improved node classification accuracy on large graphs.

Reduced training time and computational costs.

Effective capture of multi-scale dependencies.

Abstract

Graph convolutional networks (GCNs) allow us to learn topologically-aware node embeddings, which can be useful for classification or link prediction. However, they are unable to capture long-range dependencies between nodes without adding additional layers -- which in turn leads to over-smoothing and increased time and space complexity. Further, the complex dependencies between nodes make mini-batching challenging, limiting their applicability to large graphs. We propose a Scalable Multi-resolution Graph Representation Learning (SMGRL) framework that enables us to learn multi-resolution node embeddings efficiently. Our framework is model-agnostic and can be applied to any existing GCN model. We dramatically reduce training costs by training only on a reduced-dimension coarsening of the original graph, then exploit self-similarity to apply the resulting algorithm at multiple resolutions. The resulting multi-resolution embeddings can be aggregated to yield high-quality node embeddings that capture both long- and short-range dependencies. Our experiments show that this leads to improved classification accuracy, without incurring high computational costs.