Ego-CNN: Distributed, Egocentric Representations of Graphs for Detecting Critical Structures

TL;DR

Ego-CNNs are a novel graph embedding model that uses ego-centric convolutions to accurately detect critical structures at a global scale, aiding task performance and interpretability.

Contribution

The paper introduces Ego-CNNs, a new graph embedding approach that employs ego-convolutions for precise critical structure detection and improved efficiency.

Findings

Achieves comparable performance to state-of-the-art models

Effectively visualizes detected structures with CNN techniques

Enhances training efficiency with scale-free priors

Abstract

We study the problem of detecting critical structures using a graph embedding model. Existing graph embedding models lack the ability to precisely detect critical structures that are specific to a task at the global scale. In this paper, we propose a novel graph embedding model, called the Ego-CNNs, that employs the ego-convolutions convolutions at each layer and stacks up layers using an ego-centric way to detects precise critical structures efficiently. An Ego-CNN can be jointly trained with a task model and help explain/discover knowledge for the task. We conduct extensive experiments and the results show that Ego-CNNs (1) can lead to comparable task performance as the state-of-the-art graph embedding models, (2) works nicely with CNN visualization techniques to illustrate the detected structures, and (3) is efficient and can incorporate with scale-free priors, which commonly occurs in social network datasets, to further improve the training efficiency.