all AI news
HCL: Improving Graph Representation with Hierarchical Contrastive Learning. (arXiv:2210.12020v1 [cs.LG])
cs.LG updates on arXiv.org arxiv.org
Contrastive learning has emerged as a powerful tool for graph representation
learning. However, most contrastive learning methods learn features of graphs
with fixed coarse-grained scale, which might underestimate either local or
global information. To capture more hierarchical and richer representation, we
propose a novel Hierarchical Contrastive Learning (HCL) framework that
explicitly learns graph representation in a hierarchical manner. Specifically,
HCL includes two key components: a novel adaptive Learning to Pool (L2Pool)
method to construct more reasonable multi-scale graph topology for …
arxiv graph graph representation hcl hierarchical representation