Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework

09/11/2020
by   Aravind Sankar, et al.
0

We present InfoMotif, a new semi-supervised, motif-regularized, learning framework over graphs. We overcome two key limitations of message passing in popular graph neural networks (GNNs): localization (a k-layer GNN cannot utilize features outside the k-hop neighborhood of the labeled training nodes) and over-smoothed (structurally indistinguishable) representations. We propose the concept of attributed structural roles of nodes based on their occurrence in different network motifs, independent of network proximity. Two nodes share attributed structural roles if they participate in topologically similar motif instances over co-varying sets of attributes. Further, InfoMotif achieves architecture independence by regularizing the node representations of arbitrary GNNs via mutual information maximization. Our training curriculum dynamically prioritizes multiple motifs in the learning process without relying on distributional assumptions in the underlying graph or the learning task. We integrate three state-of-the-art GNNs in our framework, to show significant gains (3-10 gains for nodes with sparse training labels and diverse attributes in local neighborhood structures.

READ FULL TEXT

page 1

page 9

09/06/2019

NEAR: Neighborhood Edge AggregatoR for Graph Classification

Learning graph-structured data with graph neural networks (GNNs) has bee...
10/27/2019

Pre-train and Learn: Preserve Global Information for Graph Neural Networks

Graph neural networks (GNNs) have shown great power in learning on attri...
06/11/2021

Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns

Graph neural networks (GNNs) have achieved tremendous success on multipl...
02/17/2021

Ego-based Entropy Measures for Structural Representations on Graphs

Machine learning on graph-structured data has attracted high research in...
02/18/2022

Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction

Graph neural networks (GNNs) have drawn significant research attention r...
05/26/2021

Local, global and scale-dependent node roles

This paper re-examines the concept of node equivalences like structural ...
03/11/2022

Graph Summarization with Graph Neural Networks

The goal of graph summarization is to represent large graphs in a struct...