all AI news
Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities. (arXiv:2204.07321v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
Graph neural networks have emerged as a leading architecture for many
graph-level tasks such as graph classification and graph generation with a
notable improvement. Among these tasks, graph pooling is an essential component
of graph neural network architectures for obtaining a holistic graph-level
representation of the entire graph. Although a great variety of methods have
been proposed in this promising and fast-developing research field, to the best
of our knowledge, little effort has been made to systematically summarize these
methods. …
arxiv challenges graph graph neural networks networks neural networks pooling progress