ENADPool: The Edge-Node Attention-based Differentiable Pooling for Graph Neural Networks

arXiv:2405.10218v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) are powerful tools for graph classification. One important operation for GNNs is the downsampling or pooling that can learn effective embeddings from the node representations. In this paper, we propose a new hierarchical pooling operation, namely the Edge-Node Attention-based Differentiable Pooling (ENADPool), for GNNs to learn effective graph representations. Unlike the classical hierarchical pooling operation that is based on the unclear node assignment and simply computes the averaged feature over the …

abstract arxiv attention classification cs.ai cs.lg differentiable downsampling edge embeddings gnns graph graph neural networks hierarchical learn networks neural networks node paper pooling the edge tools type