Stacked Graph Filter

11/22/2020
by   Hoang NT, et al.
0

We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully connected weights versus trainable polynomial coefficients. We find that by stacking graph filters with learnable polynomial parameters, we can build a highly adaptive and robust vertex classification model. Our treatment here relaxes the low-frequency (or equivalently, high homophily) assumptions in existing vertex classification models, resulting a more ubiquitous solution in terms of spectral properties. Empirically, by using only one hyper-parameter setting, our model achieves strong results on most benchmark datasets across the frequency spectrum.

READ FULL TEXT
research
07/10/2021

Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering

Graph convolutional networks are becoming indispensable for deep learnin...
research
04/26/2021

Graph Neural Networks with Adaptive Frequency Response Filter

Graph Neural Networks have recently become a prevailing paradigm for var...
research
10/14/2021

SoGCN: Second-Order Graph Convolutional Networks

Graph Convolutional Networks (GCN) with multi-hop aggregation is more ex...
research
07/01/2020

From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation

Graph convolutional networks (GCN) have been recently applied to semi-su...
research
01/06/2019

LanczosNet: Multi-Scale Deep Graph Convolutional Networks

We propose the Lanczos network (LanczosNet), which uses the Lanczos algo...
research
07/18/2017

Spectral Filter Tracking

Visual object tracking is a challenging computer vision task with numero...
research
06/28/2020

VPNet: Variable Projection Networks

In this paper, we introduce VPNet, a novel model-driven neural network a...

Please sign up or login with your details

Forgot password? Click here to reset