Node Proximity Is All You Need: Unified Structural and Positional Node and Graph Embedding

TL;DR

This paper introduces PhUSION, a unified framework for structural and positional node embeddings that leverages node proximity scores, providing a comprehensive approach for node and graph-level machine learning across diverse datasets.

Contribution

The paper presents PhUSION, a novel proximity-based framework that unifies structural and positional node embeddings and clarifies their generation process, enhancing graph feature learning.

Findings

PhUSION effectively captures structural and positional information.

Aggregated embeddings improve graph-level feature representation.

Systematic empirical study validates successful design choices.

Abstract

While most network embedding techniques model the relative positions of nodes in a network, recently there has been significant interest in structural embeddings that model node role equivalences, irrespective of their distances to any specific nodes. We present PhUSION, a proximity-based unified framework for computing structural and positional node embeddings, which leverages well-established methods for calculating node proximity scores. Clarifying a point of contention in the literature, we show which step of PhUSION produces the different kinds of embeddings and what steps can be used by both. Moreover, by aggregating the PhUSION node embeddings, we obtain graph-level features that model information lost by previous graph feature learning and kernel methods. In a comprehensive empirical study with over 10 datasets, 4 tasks, and 35 methods, we systematically reveal successful design choices for node and graph-level machine learning with embeddings.