Feature Propagation on Graph: A New Perspective to Graph Representation Learning

TL;DR

This paper investigates the convergence properties of feature propagation in graph representation learning, establishing conditions for stability, linking to existing methods, and extending to edge-based approaches with practical fraud detection applications.

Contribution

It formally defines feature propagation, analyzes its convergence conditions, connects it to established methods, and introduces edge2vec with real-world fraud detection applications.

Findings

Convergence conditions for feature propagation are established.

Feature propagation is linked to node2vec and structure2vec.

Edge2vec demonstrates competitive performance in fraud detection.

Abstract

We study feature propagation on graph, an inference process involved in graph representation learning tasks. It's to spread the features over the whole graph to the $t$-th orders, thus to expand the end's features. The process has been successfully adopted in graph embedding or graph neural networks, however few works studied the convergence of feature propagation. Without convergence guarantees, it may lead to unexpected numerical overflows and task failures. In this paper, we first define the concept of feature propagation on graph formally, and then study its convergence conditions to equilibrium states. We further link feature propagation to several established approaches such as node2vec and structure2vec. In the end of this paper, we extend existing approaches from represent nodes to edges (edge2vec) and demonstrate its applications on fraud transaction detection in real world scenario. Experiments show that it is quite competitive.