Relational Pooling for Graph Representations
It addresses the problem of limited representation power in graph learning for researchers and practitioners, offering a theoretically sound approach that can enhance existing models.
The paper tackles the limitation of graph neural networks (GNNs) by introducing Relational Pooling (RP), a framework that generalizes GNNs beyond existing methods like Weisfeiler-Lehman, achieving improved performance on graph classification tasks.
This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-Lehman (WL) algorithm, graph Laplacians, and diffusions. Our approach, denoted Relational Pooling (RP), draws from the theory of finite partial exchangeability to provide a framework with maximal representation power for graphs. RP can work with existing graph representation models and, somewhat counterintuitively, can make them even more powerful than the original WL isomorphism test. Additionally, RP allows architectures like Recurrent Neural Networks and Convolutional Neural Networks to be used in a theoretically sound approach for graph classification. We demonstrate improved performance of RP-based graph representations over state-of-the-art methods on a number of tasks.