Ego-CNN: Distributed, Egocentric Representations of Graphs for Detecting Critical Structures
This addresses the challenge of precise critical structure detection in graph analysis, which is incremental as it builds on existing graph embedding methods.
The paper tackles the problem of detecting critical structures in graphs by proposing Ego-CNN, a novel graph embedding model that uses ego-convolutions to efficiently identify task-specific structures globally, achieving comparable performance to state-of-the-art models and improving training efficiency with scale-free priors.
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.