SaaN 2L-GRL: Two-Level Graph Representation Learning Empowered With Subgraph-as-a-Node

In this study, we propose a novel graph representation learning (GRL) model, called Two-Level GRL with Subgraph-as-a-Node (SaaN 2L-GRL in short), that partitions input graphs into smaller subgraphs for effective and scalable GRL in two levels: 1) local GRL and 2) global GRL. To realize the two-level GRL in an efficient manner, we propose an abstracted graph, called Subgraph-as-a-Node Graph (SaaN in short), to effectively maintain the high-level graph topology while significantly reducing the size of the graph. By applying the SaaN graph to both local and global GRL, SaaN 2L-GRL can effectively preserve the overall structure of the entire graph while precisely representing the nodes within each subgraph. Through time complexity analysis, we confirm that SaaN 2L-GRL significantly reduces the learning time of existing GRL models by using the SaaN graph for global GRL, instead of using the original graph, and processing local GRL on subgraphs in parallel. Our extensive experiments show that SaaN 2L-GRL outperforms existing GRL models in both accuracy and efficiency. In addition, we show the effectiveness of SaaN 2L-GRL using diverse kinds of graph partitioning methods, including five community detection algorithms and representative edge- and vertex-cut algorithms.

I. Introduction

Graphs have been widely used to represent complex relationships between objects effectively [1]. A graph consists of nodes, the fundamental units, and edges that represent connections between two nodes [2]. Real-world applications using graphs encompass diverse domains, including social networks, road networks, autonomous driving systems, and web graphs, where graph structures can represent relationships (i.e., edges) between different objects (i.e., nodes). Many organizations, such as Airbnb, NBC News, and NASA, use graph databases to manage their businesses [3]. In the healthcare industry, AstraZeneca analyzes graph data to find patients with similar travel patterns and health conditions [4]. The U.S. Army also uses a graph database to manage and track equipment maintenance across thousands of vehicles, parts, and locations worldwide [5].