A Representation Learning Framework for Property Graphs

TL;DR

This paper introduces PGE, a novel graph embedding framework that effectively incorporates both node and edge properties, improving performance on tasks like node classification and link prediction.

Contribution

PGE is the first framework to integrate node and edge properties into graph embeddings using a biased neighbor sampling strategy.

Findings

PGE outperforms state-of-the-art methods on benchmark datasets.

Incorporating properties enhances embedding quality for classification and prediction.

The framework is scalable and effective for real-world property graphs.

Abstract

Representation learning on graphs, also called graph embedding, has demonstrated its significant impact on a series of machine learning applications such as classification, prediction and recommendation. However, existing work has largely ignored the rich information contained in the properties (or attributes) of both nodes and edges of graphs in modern applications, e.g., those represented by property graphs. To date, most existing graph embedding methods either focus on plain graphs with only the graph topology, or consider properties on nodes only. We propose PGE, a graph representation learning framework that incorporates both node and edge properties into the graph embedding procedure. PGE uses node clustering to assign biases to differentiate neighbors of a node and leverages multiple data-driven matrices to aggregate the property information of neighbors sampled based on a biased strategy. PGE adopts the popular inductive model for neighborhood aggregation. We provide detailed analyses on the efficacy of our method and validate the performance of PGE by showing how PGE achieves better embedding results than the state-of-the-art graph embedding methods on benchmark applications such as node classification and link prediction over real-world datasets.