Ising on the Graph: Task-specific Graph Subsampling via the Ising Model

arXiv:2402.10206v1 Announce Type: new
Abstract: Reducing a graph while preserving its overall structure is an important problem with many applications. Typically, the reduction approaches either remove edges (sparsification) or merge nodes (coarsening) in an unsupervised way with no specific downstream task in mind. In this paper, we present an approach for subsampling graph structures using an Ising model defined on either the nodes or edges and learning the external magnetic field of the Ising model using a graph neural network. …

abstract applications arxiv cs.ai cs.lg graph merge mind nodes paper type unsupervised via