Second-Order Pooling for Graph Neural Networks

TL;DR

This paper introduces second-order pooling techniques for graph neural networks, addressing challenges of variable graph sizes and isomorphism, and demonstrates their effectiveness in graph classification tasks.

Contribution

It proposes novel second-order pooling methods, including bilinear and attentional pooling, for improved graph representation learning in GNNs.

Findings

Significant performance improvements on graph classification tasks.

Effective use of all node information through second-order statistics.

Hierarchical pooling extension enhances flexibility in GNNs.

Abstract

Graph neural networks have achieved great success in learning node representations for graph tasks such as node classification and link prediction. Graph representation learning requires graph pooling to obtain graph representations from node representations. It is challenging to develop graph pooling methods due to the variable sizes and isomorphic structures of graphs. In this work, we propose to use second-order pooling as graph pooling, which naturally solves the above challenges. In addition, compared to existing graph pooling methods, second-order pooling is able to use information from all nodes and collect second-order statistics, making it more powerful. We show that direct use of second-order pooling with graph neural networks leads to practical problems. To overcome these problems, we propose two novel global graph pooling methods based on second-order pooling; namely, bilinear mapping and attentional second-order pooling. In addition, we extend attentional second-order pooling to hierarchical graph pooling for more flexible use in GNNs. We perform thorough experiments on graph classification tasks to demonstrate the effectiveness and superiority of our proposed methods. Experimental results show that our methods improve the performance significantly and consistently.