Eigen-GNN swMATH ID: 38084 Software Authors: Ziwei Zhang, Peng Cui, Jian Pei, Xin Wang, Wenwu Zhu Description: Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs. 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. Homepage: https://arxiv.org/abs/2006.04330 Keywords: Machine Learning; arXiv_cs.LG; arXiv_stat.ML; Graph Neural Networks; GNNs; Plug-in; Eigen-GNN Related Software: PairNorm; DropEdge; GraphSAGE; DeepGCNs; AutoKeras; LightGBM; PyTorch-BigGraph; NetLSD; AutoNE; DGL; AliGraph; PyTorch; auto-sklearn; Python; AutoGL Cited in: 0 Documents Standard Articles 1 Publication describing the Software Year Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs Ziwei Zhang, Peng Cui, Jian Pei, Xin Wang, Wenwu Zhu 2020