Control-based Graph Embeddings with Data Augmentation for Contrastive Learning

arXiv:2403.04923v1 Announce Type: new
Abstract: In this paper, we study the problem of unsupervised graph representation learning by harnessing the control properties of dynamical networks defined on graphs. Our approach introduces a novel framework for contrastive learning, a widely prevalent technique for unsupervised representation learning. A crucial step in contrastive learning is the creation of 'augmented' graphs from the input graphs. Though different from the original graphs, these augmented graphs retain the original graph's structural characteristics. Here, we propose a …

abstract arxiv augmentation control cs.lg cs.ma cs.sy data eess.sy embeddings framework graph graph representation graphs networks novel paper representation representation learning study type unsupervised