Awesome-Graph-Condensation

🚩 We have released a new survey paper, presenting a comprehensive overview of existing graph condensation methods. We are looking forward to any comments or discussions on this topic :)

What is GC

Given that graph data consists of a massive number of nodes and their relationships, Graph Condensation (GC) solves the problem of: How to condense large-scale graphs into smaller yet informative ones.

How can this repository be of service

This repository contains a list of papers who shares a common motivation of GC; We categorize them based on their aspect of making condensed graphs informative, i.e., what information of the original graph was designed to preserve, the graph properties (graph guided) or the trained models' capabilities (model guided).

We will try to make this list updated. If you found any error or any missed paper, please don't hesitate to open an issue or pull request.

Paper List

Survey Paper	Conference
🚩 A Survey on Graph Condensation	arXiv 2024
Graph Condensation: A Survey	arXiv 2024
A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation	arXiv 2024

Category	Paper	Method	Conference	Code
Graph Guided	Graph reduction with spectral and cut guarantees	GC	JMLR 2019	Python
Graph Guided	A unifying framework for spectrum-preserving graph sparsification and coarsening	ReduceG	NIPS 2019	Python
Graph Guided	Scaling up graph neural networks via graph coarsening	SCAL	KDD 2021	Pytorch
Graph Guided	GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding	GraphZoom	ICLR 2020	Python
Graph Guided	Graph coarsening with preserved spectral properties	SC	ICAIS 2020	Python
Graph Guided	Featured graph coarsening with similarity guarantees	FGC	ICML 2023	-
Graph Guided	Cat: Balanced continual graph learning with graph condensation	CaT	ICDM 2023	Pytorch
Graph Guided	Unsupervised learning of graph hierarchical abstractions with differentiable coarsening and optimal transport	OTC	AAAI 2021	Pytorch
Modle Guided	Graph coarsening via convolution matching for scalable graph neural network training	ConvMatch	aiXiv 2023	Pytorch
Modle Guided	Graph Condensation via Receptive Field Distribution Matching	GCDM	aiXiv 2022	-
Modle Guided	Kernel Ridge Regression-Based Graph Dataset Distillation	KiDD	KDD 2023	Pytorch
Modle Guided	FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks	FedGKD	aiXiv 2023	-
Modle Guided	Fast graph condensation with structure-based neural tangent kernel	GC-SNTK	aiXiv 2023	-
Modle Guided	Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data	SFGC	NIPS 2023	Pytorch
Modle Guided	Condensing Graphs via One-Step Gradient Matching	DosCond	KDD 2022	Pytorch
Modle Guided	Graph condensation for graph neural networks	GCond	ICLR 2021	Pytorch
Modle Guided	Attend who is weak: Enhancing graph condensation via cross-free adversarial training	GroC	aiXiv 2023	-
Modle Guided	Faster Hyperparameter Search for GNNs via Calibrated Dataset Condensation	HCDC	OpenReview 2023	-
Modle Guided	Multiple sparse graphs condensation	MSGC	Knowledge-Based Systems 2023	-
Hybrid	Graph condensation for inductive node representation learning	Mcond	aiXiv 2023	-
Hybrid	Does graph distillation see like vision dataset counterpart?	SGDD	NIPS 2023	Pytorch
Hybrid	Graph condensation via eigenbasis matching	GCEM	aiXiv 2023	-