DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters

Abstract

We propose a novel spectral convolutional neural network (CNN) model on graph structured data, namely Distributed Feedback-Looped Networks (DFNets). This model is incorporated with a robust class of spectral graph filters, called feedback-looped filters, to provide better localization on vertices, while still attaining fast convergence and linear memory requirements. Theoretically, feedback-looped filters can guarantee convergence w.r.t. a specified error bound, and be applied universally to any graph without knowing its structure. Furthermore, the propagation rule of this model can diversify features from the preceding layers to produce strong gradient flows. We have evaluated our model using two benchmark tasks: semi-supervised document classification on citation networks and semi-supervised entity classification on a knowledge graph. The experimental results show that our model considerably outperforms the state-of-the-art methods in both benchmark tasks over all datasets.

arXiv comment33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

References in corpus (7)

• 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
• Deep Convolutional Networks on Graph-Structured Data
• Graph Neural Networks with convolutional ARMA filters
• L2 Regularization for Learning Kernels
• Autoregressive Moving Average Graph Filtering
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks

Cited by in corpus (2)

• Regular Splitting Graph Network for 3D Human Pose Estimation
• A Consistent Diffusion-Based Algorithm for Semi-Supervised Classification on Graphs