SPAGAN: Shortest Path Graph Attention Network

01/10/2021
by   Yiding Yang, et al.
0

Graph convolutional networks (GCN) have recently demonstrated their potential in analyzing non-grid structure data that can be represented as graphs. The core idea is to encode the local topology of a graph, via convolutions, into the feature of a center node. In this paper, we propose a novel GCN model, which we term as Shortest Path Graph Attention Network (SPAGAN). Unlike conventional GCN models that carry out node-based attentions within each layer, the proposed SPAGAN conducts path-based attention that explicitly accounts for the influence of a sequence of nodes yielding the minimum cost, or shortest path, between the center node and its higher-order neighbors. SPAGAN therefore allows for a more informative and intact exploration of the graph structure and further a more effective aggregation of information from distant neighbors into the center node, as compared to node-based GCN methods. We test SPAGAN on the downstream classification task on several standard datasets, and achieve performances superior to the state of the art. Code is publicly available at https://github.com/ihollywhy/SPAGAN.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/19/2020

Node Similarity Preserving Graph Convolutional Networks

Graph Neural Networks (GNNs) have achieved tremendous success in various...
03/30/2020

L^2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks

Graph convolution networks (GCN) are increasingly popular in many applic...
09/04/2021

Node Feature Kernels Increase Graph Convolutional Network Robustness

The robustness of the much-used Graph Convolutional Networks (GCNs) to p...
10/28/2021

RGP: Neural Network Pruning through Its Regular Graph Structure

Lightweight model design has become an important direction in the applic...
03/02/2020

Permutohedral-GCN: Graph Convolutional Networks with Global Attention

Graph convolutional networks (GCNs) update a node's feature vector by ag...
08/11/2021

GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks

In this paper, we present GCN-Denoiser, a novel feature-preserving mesh ...
09/15/2017

On the stability of network indices defined by means of matrix functions

Identifying important components in a network is one of the major goals ...