Keywords: Graph coarsening, node classification, graph neural network
TL;DR: This work developed an optimization-based framework for learning a high-quality coarsened graph, which incorporates the graph matrix, feature matrix, and some node label information from the original graph.
Abstract: In data-intensive applications, graphs serve as foundational structures across various domains. However, the increasing size of datasets poses significant challenges to performing downstream tasks. To address this problem, techniques such as graph coarsening, condensation, and summarization have been developed to create a coarsened graph while preserving important properties of the original graph by considering both the graph matrix and the feature or attribute matrix of the original graph as inputs. However, existing graph coarsening techniques often neglect the label information during the coarsening process, which can result in a lower-quality coarsened graph and limit its suitability for downstream tasks. To overcome this limitation, we introduce the Label-Aware Graph Coarsening (LAGC) algorithm, a semi-supervised approach that incorporates the graph matrix, feature matrix, and some of the node label information to learn a coarsened graph. Our proposed formulation is a non-convex optimization problem that is efficiently solved using block successive upper bound minimization(BSUM) technique, and it is provably convergent. Our extensive results demonstrate that the LAGC algorithm outperforms the existing state-of-the-art method by a significant margin.
Supplementary Material: zip
List Of Authors: Kumar, Manoj and Halder, Subhanu and Kane, Archit and Gupta, Ruchir and Kumar, Sandeep
Latex Source Code: zip
Signed License Agreement: pdf
Code Url: https://github.com/Archit2000/LAGC
Submission Number: 599
Loading