Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs

Abstract

Graph Neural Networks (GNNs) are emerging machine learning models on graphs. Although sufficiently deep GNNs are shown theoretically capable of fully preserving graph structures, most existing GNN models in practice are shallow and essentially feature-centric. We show empirically and analytically that the existing shallow GNNs cannot preserve graph structures well. To overcome this fundamental challenge, we propose Eigen-GNN, a simple yet effective and general plug-in module to boost GNNs ability in preserving graph structures. Specifically, we integrate the eigenspace of graph structures with GNNs by treating GNNs as a type of dimensionality reduction and expanding the initial dimensionality reduction bases. Without needing to increase depths, Eigen-GNN possesses more flexibilities in handling both feature-driven and structure-driven tasks since the initial bases contain both node features and graph structures. We present extensive experimental results to demonstrate the effectiveness of Eigen-GNN for tasks including node classification, link prediction, and graph isomorphism tests.

arXiv comment11 pages plus 8 pages for appendices, 4 figures

References in corpus (10)

• Distributed Representations of Words and Phrases and their Compositionality
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Graph Neural Networks: A Review of Methods and Applications
• Social Structure of Facebook Networks
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Invariant and Equivariant Graph Networks
• Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
• Measuring and Improving the Use of Graph Information in Graph Neural Networks