Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks

03/18/2020
by   Yimeng Min, et al.
5

Graph convolutional networks (GCNs) have shown promising results in processing graph data by extracting structure-aware features. This gave rise to extensive work in geometric deep learning, focusing on designing network architectures that ensure neuron activations conform to regularity patterns within the input graph. However, in most cases the graph structure is only accounted for by considering the similarity of activations between adjacent nodes, which in turn degrades the results. In this work, we augment GCN models by incorporating richer notions of regularity by leveraging cascades of band-pass filters, known as geometric scatterings. The produced graph features incorporate multiscale representations of local graph structures, while avoiding overly smooth activations forced by previous architectures. Moreover, inspired by skip connections used in residual networks, we introduce graph residual convolutions that reduce high-frequency noise caused by joining together information at multiple scales. Our hybrid architecture introduces a new model for semi-supervised learning on graph-structured data, and its potential is demonstrated for node classification tasks on multiple graph datasets, where it outperforms leading GCN models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/22/2022

Overcoming Oversmoothness in Graph Convolutional Networks via Hybrid Scattering Networks

Geometric deep learning (GDL) has made great strides towards generalizin...
research
07/02/2019

Structure fusion based on graph convolutional networks for semi-supervised classification

Suffering from the multi-view data diversity and complexity for semi-sup...
research
10/06/2020

Data-Driven Learning of Geometric Scattering Networks

Graph neural networks (GNNs) in general, and graph convolutional network...
research
04/10/2022

ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classification

Compared to sequential learning models, graph-based neural networks exhi...
research
05/03/2021

Schema-Aware Deep Graph Convolutional Networks for Heterogeneous Graphs

Graph convolutional network (GCN) based approaches have achieved signifi...
research
01/27/2020

Efficient and Stable Graph Scattering Transforms via Pruning

Graph convolutional networks (GCNs) have well-documented performance in ...
research
11/25/2022

Cross-network transferable neural models for WLAN interference estimation

Airtime interference is a key performance indicator for WLANs, measuring...

Please sign up or login with your details

Forgot password? Click here to reset