Diffusion improves graph learning

J Gasteiger, S Weißenberger… - Advances in neural …, 2019 - proceedings.neurips.cc
Graph convolution is the core of most Graph Neural Networks (GNNs) and usually
approximated by message passing between direct (one-hop) neighbors. In this work, we …

Diffusion-convolutional neural networks

J Atwood, D Towsley - Advances in neural information …, 2016 - proceedings.neurips.cc
We present diffusion-convolutional neural networks (DCNNs), a new model for graph-
structured data. Through the introduction of a diffusion-convolution operation, we show how …

Simple spectral graph convolution

H Zhu, P Koniusz - International conference on learning …, 2021 - openreview.net
Graph Convolutional Networks (GCNs) are leading methods for learning graph
representations. However, without specially designed architectures, the performance of …

Dual graph convolutional networks for graph-based semi-supervised classification

C Zhuang, Q Ma - Proceedings of the 2018 world wide web conference, 2018 - dl.acm.org
The problem of extracting meaningful data through graph analysis spans a range of different
fields, such as the internet, social networks, biological networks, and many others. The …

An empirical study of graph contrastive learning

Y Zhu, Y Xu, Q Liu, S Wu - ar** for graph classification
Y Wang, W Wang, Y Liang, Y Cai, B Hooi - arxiv preprint arxiv …, 2020 - arxiv.org
We present a new method to regularize graph neural networks (GNNs) for better
generalization in graph classification. Observing that the omission of sub-structures does not …