PropEnc: A Property Encoder for Graph Neural Networks

TL;DR

PropEnc is a versatile graph node encoder that generates expressive embeddings from any graph metric, addressing limitations of existing methods in scale-free and large property graphs, and improving efficiency and adaptability.

Contribution

The paper introduces PropEnc, a novel encoding method combining histogram and reversed index encoding to create flexible, low-dimensional node embeddings from diverse graph metrics.

Findings

PropEnc outperforms existing encoders in graph classification tasks.

It effectively handles graphs with large or non-categorical properties.

PropEnc improves computational efficiency and embedding expressiveness.

Abstract

Graph machine learning, particularly using graph neural networks, heavily relies on node features. However, many real-world systems, such as social and biological networks, lack node features due to privacy concerns, incomplete data, or collection limitations. Structural and positional encoding are commonly used to address this but are constrained by the maximum values of the encoded properties, such as the highest node degree. This limitation makes them impractical for scale-free networks and applications involving large or non-categorical properties. This paper introduces PropEnc, a novel and versatile encoder to generate expressive node embedding from any graph metric. By combining histogram construction with reversed index encoding, PropEnc offers a flexible solution that supports low-dimensional representations and diverse input types, effectively mitigating sparsity issues while improving computational efficiency. Additionally, it replicates one-hot encoding or approximates indices with high accuracy, making it adaptable to a wide range of graph applications. We validate PropEnc through extensive experiments on graph classification task across several social networks lacking node features. The empirical results demonstrate that PropEnc offers an efficient mechanism for constructing node features from various graph metrics.