Uncovering Capabilities of Model Pruning in Graph Contrastive Learning

J Wu, X Chen, S Li - Proceedings of the 32nd ACM International …, 2024 - dl.acm.org
Graph contrastive learning has achieved great success in pre-training graph neural
networks without ground-truth labels. Leading graph contrastive learning follows the …

GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts

Z Guo, Q Sun, H Yuan, X Fu, M Zhou, Y Gao… - arxiv preprint arxiv …, 2024 - arxiv.org
Real-world graphs have inherently complex and diverse topological patterns, known as
topological heterogeneity. Most existing works learn graph representation in a single …