Learning Optimal Propagation for Graph Neural Networks. (arXiv:2205.02998v1 [cs.LG])

Web: http://arxiv.org/abs/2205.02998

Graph Neural Networks (GNNs) have achieved tremendous success in a variety of
real-world applications by relying on the fixed graph data as input. However,
the initial input graph might not be optimal in terms of specific downstream
tasks, because of information scarcity, noise, adversarial attacks, or
discrepancies between the distribution in graph topology, features, and
groundtruth labels. In this paper, we propose a bi-level optimization-based
approach for learning the optimal graph structure via directly learning the
Personalized PageRank propagation matrix …

arxiv graph graph neural networks learning networks neural neural networks