ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations

11/18/2019
by   Ekagra Ranjan, et al.
0

Graph Neural Networks (GNN) have been shown to work effectively for modeling graph structured data to solve tasks such as node classification, link prediction and graph classification. There has been some recent progress in defining the notion of pooling in graphs whereby the model tries to generate a graph level representation by downsampling and summarizing the information present in the nodes. Existing pooling methods either fail to effectively capture the graph substructure or do not easily scale to large graphs. In this work, we propose ASAP (Adaptive Structure Aware Pooling), a sparse and differentiable pooling method that addresses the limitations of previous graph pooling architectures. ASAP utilizes a novel self-attention network along with a modified GNN formulation to capture the importance of each node in a given graph. It also learns a sparse soft cluster assignment for nodes at each layer to effectively pool the subgraphs to form the pooled graph. Through extensive experiments on multiple datasets and theoretical analysis, we motivate our choice of the components used in ASAP. Our experimental results show that combining existing GNN architectures with ASAP leads to state-of-the-art results on multiple graph classification benchmarks. ASAP has an average improvement of 4%, compared to current sparse hierarchical state-of-the-art method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/22/2018

Hierarchical Graph Representation Learning withDifferentiable Pooling

Recently, graph neural networks (GNNs) have revolutionized the field of ...
research
06/22/2018

Hierarchical Graph Representation Learning with Differentiable Pooling

Recently, graph neural networks (GNNs) have revolutionized the field of ...
research
04/27/2021

Structure-Aware Hierarchical Graph Pooling using Information Bottleneck

Graph pooling is an essential ingredient of Graph Neural Networks (GNNs)...
research
06/11/2022

Soft-mask: Adaptive Substructure Extractions for Graph Neural Networks

For learning graph representations, not all detailed structures within a...
research
06/26/2022

Structural Entropy Guided Graph Hierarchical Pooling

Following the success of convolution on non-Euclidean space, the corresp...
research
04/13/2021

Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning

Graph neural networks (GNN) have been proven to be mature enough for han...
research
12/17/2019

Multi-Channel Graph Convolutional Networks

Graph neural networks (GNN) has been demonstrated to be effective in cla...

Please sign up or login with your details

Forgot password? Click here to reset