Node Proximity Is All You Need: Unified Structural and Positional Node and Graph Embedding
This work addresses the challenge of integrating structural and positional embeddings for network analysis, which is incremental as it builds on existing proximity methods to unify and clarify approaches.
The authors tackled the problem of unifying structural and positional node embeddings in networks by introducing PhUSION, a proximity-based framework that clarifies how different embeddings are produced and aggregates them for graph-level features. The result is a comprehensive empirical study across over 10 datasets, 4 tasks, and 35 methods, systematically revealing successful design choices for node and graph-level machine learning.
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.