DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters

10/24/2019
by   Asiri Wijesinghe, et al.
0

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.

READ FULL TEXT
research
09/09/2016

Semi-Supervised Classification with Graph Convolutional Networks

We present a scalable approach for semi-supervised learning on graph-str...
research
11/25/2018

Graph Learning-Convolutional Networks

Recently, graph Convolutional Neural Networks (graph CNNs) have been wid...
research
01/05/2019

Graph Neural Networks with distributed ARMA filters

Recent graph neural networks implement convolutional layers based on pol...
research
09/29/2020

Framework for Designing Filters of Spectral Graph Convolutional Neural Networks in the Context of Regularization Theory

Graph convolutional neural networks (GCNNs) have been widely used in gra...
research
01/28/2019

Generalized Label Propagation Methods for Semi-Supervised Learning

The key challenge in semi-supervised learning is how to effectively leve...
research
03/02/2017

Robust Spatial Filtering with Graph Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have recently led to incredible bre...
research
09/30/2018

Graph Spectral Regularization for Neural Network Interpretability

Deep neural networks can learn meaningful representations of data. Howev...

Please sign up or login with your details

Forgot password? Click here to reset