Subgraph Frequency Distribution Estimation using Graph Neural Networks

TL;DR

This paper introduces GNNS, a graph neural network-based framework that efficiently estimates subgraph frequency distributions, achieving comparable accuracy to existing methods but with significantly improved speed, enabling scalable analysis of large networks.

Contribution

The paper presents a novel GNN-based framework with hierarchical embeddings for fast, scalable subgraph frequency estimation, outperforming existing methods in speed.

Findings

Achieves three orders of magnitude speedup over existing methods.

Maintains comparable accuracy in subgraph frequency estimation.

Enables scalable analysis of large networks.

Abstract

Small subgraphs (graphlets) are important features to describe fundamental units of a large network. The calculation of the subgraph frequency distributions has a wide application in multiple domains including biology and engineering. Unfortunately due to the inherent complexity of this task, most of the existing methods are computationally intensive and inefficient. In this work, we propose GNNS, a novel representational learning framework that utilizes graph neural networks to sample subgraphs efficiently for estimating their frequency distribution. Our framework includes an inference model and a generative model that learns hierarchical embeddings of nodes, subgraphs, and graph types. With the learned model and embeddings, subgraphs are sampled in a highly scalable and parallel way and the frequency distribution estimation is then performed based on these sampled subgraphs. Eventually, our methods achieve comparable accuracy and a significant speedup by three orders of magnitude compared to existing methods.