REVIEW 4 cited by
A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Many real-world datasets can be naturally represented as graphs, spanning a wide range of domains. However, the increasing complexity and size of graph datasets present significant challenges for analysis and computation. In response, graph reduction, or graph summarization, has gained prominence for simplifying large graphs while preserving essential properties. In this survey, we aim to provide a comprehensive understanding of graph reduction methods, including graph sparsification, graph coarsening, and graph condensation. Specifically, we establish a unified definition for these methods and introduce a hierarchical taxonomy to categorize the challenges they address. Our survey then systematically reviews the technical details of these methods and emphasizes their practical applications across diverse scenarios. Furthermore, we outline critical research directions to ensure the continued effectiveness of graph reduction techniques, as well as provide a comprehensive paper list at \url{https://github.com/Emory-Melody/awesome-graph-reduction}. We hope this survey will bridge literature gaps and propel the advancement of this promising field.
Forward citations
Cited by 4 Pith papers
-
Simple yet Effective Graph Distillation via Clustering
ClustGDD distills large graphs by clustering node embeddings and refining synthetic attributes, achieving state-of-the-art node classification accuracy at orders of magnitude lower time cost.
-
GCAL: Adapting Graph Models to Evolving Domain Shifts
GCAL combines information-maximization adaptation with variational memory graph generation to prevent catastrophic forgetting in unsupervised continual graph domain adaptation.
-
SGS-GNN: A Supervised Graph Sparsification method for Graph Neural Networks
A supervised edge-sampling sparsifier that keeps only 20% of edges can match or beat the full graph for GNN node classification, with especially large gains on heterophilic graphs.
-
Heterogeneous Graph Condensation via Role-Aware Clustering
Role-aware clustering (class-partitioned targets, type-wise non-targets) plus cluster-level reconstruction yields compact heterogeneous graphs that train HGNNs near full-graph accuracy at far lower condensation cost.
Discussion (0). Sign in to comment.