Topology-Aware Graph Pooling Networks

10/19/2020
by   Hongyang Gao, et al.
6

Pooling operations have shown to be effective on computer vision and natural language processing tasks. One challenge of performing pooling operations on graph data is the lack of locality that is not well-defined on graphs. Previous studies used global ranking methods to sample some of the important nodes, but most of them are not able to incorporate graph topology. In this work, we propose the topology-aware pooling (TAP) layer that explicitly considers graph topology. Our TAP layer is a two-stage voting process that selects more important nodes in a graph. It first performs local voting to generate scores for each node by attending each node to its neighboring nodes. The scores are generated locally such that topology information is explicitly considered. In addition, graph topology is incorporated in global voting to compute the importance score of each node globally in the entire graph. Altogether, the final ranking score for each node is computed by combining its local and global voting scores. To encourage better graph connectivity in the sampled graph, we propose to add a graph connectivity term to the computation of ranking scores. Results on graph classification tasks demonstrate that our methods achieve consistently better performance than previous methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/30/2020

Structure-Feature based Graph Self-adaptive Pooling

Various methods to deal with graph data have been proposed in recent yea...
research
03/07/2023

MPool: Motif-Based Graph Pooling

Graph Neural networks (GNNs) have recently become a powerful technique f...
research
05/11/2019

Graph U-Nets

We consider the problem of representation learning for graph data. Convo...
research
06/22/2023

On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling

A pooling operation is essential for effective graph-level representatio...
research
07/05/2019

Graph Representation Learning via Hard and Channel-Wise Attention Networks

Attention operators have been widely applied in various fields, includin...
research
06/26/2022

TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification

Learning unbiased node representations under class-imbalanced graph data...
research
06/21/2020

TreeRNN: Topology-Preserving Deep GraphEmbedding and Learning

In contrast to the literature where the graph local patterns are capture...

Please sign up or login with your details

Forgot password? Click here to reset