Graph Condensation Papers

Graph condensation (GC) is a data-centric approach that accelerates GNN model training by creating a compact yet representative graph to replace the original graph. It enables GNNs trained on the condensed graph to match the performance of those trained on the original graph.

This repository aims to provide a comprehensive resource for researchers and practitioners interested in exploring various aspects of graph condensation.

For a detailed overview of graph condensation techniques and their applications, we recommend reading our survey paper on TKDE'25: 🔥Graph Condensation: A Survey and attending our tutorial on WWW'25🔥Graph Condensation: Foundations, Methods and Prospects. The survey paper serves as an excellent starting point for understanding the fundamentals of graph condensation and exploring its diverse applications.

Latest Updates

[02/03/2025] Scalable Graph Condensation with Evolving Capabilities (Shengbo Gong et al. Arxiv'25)
[02/02/2025] Exploring Hypergraph Condensation via Variational Hyperedge Generation and Multi-Aspectual Amelioration (Zheng Gong et al. WWW'25)
[01/02/2025] Random Walk Guided Hyperbolic Graph Distillation (Yunbo Long et al. Arxiv'25)
[09/01/2025] Efficient Graph Condensation via Gaussian Process (Lin Wang et al. Arxiv'25)
[09/01/2025] GraphDART: Graph Distillation for Efficient Advanced Persistent Threat Detection (Saba Fathi Rabooki et al. Arxiv'25)
[09/01/2025] Training-free Heterogeneous Graph Condensation via Data Selection (Yuxuan Liang et al. ICDE'25)

Contribution

We welcome contributions to enhance the breadth and depth of this repository. If you have a paper related to graph condensation that you believe should be included, please feel free to submit a pull request. Together, we can build a valuable resource for the graph condensation community.

| conference/journal'year | [paper_name](paper_link) | Authors | [[code]](code_link) |

---

Contents

The repository is organized into categories to facilitate easy navigation and exploration of papers related to graph condensation, including effectiveness, efficiency, generalization, fairness and applications.

• Graph Condensation Papers
  • Latest Updates
  • Contribution
  • Contents
  • Survey
  • Methodology
    • Effective Graph Condensation
    • Efficient Graph Condensation
    • Generalized Graph Condensation
    • Fair Graph Condensation
    • Robust Graph Condensation
  • Applications
    • Graph Continual Learning
    • Hyper-Parameter/Neural Architecture Search
    • Federated Learning
    • Inference Acceleration
    • Heterogeneous Graph
    • Hypergraph Graph
    • Security
  • Open-Source Libraries
  • Related Repositories
  • Contact

---

Survey

TKDE'25	Graph Condensation: A Survey	Xinyi Gao et al.
IJCAI'24	A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation	Mohammad Hashemi & Wei Jin et al.
Arxiv'24	A Survey on Graph Condensation	Hongjia Xu et al.

---

 

Methodology

Effective Graph Condensation

ICLR'22	GCond	Graph Condensation for Graph Neural Networks	Wei Jin et al.	[code]
KBS'23	MSGC	Multiple Sparse Graphs Condensation	Jian Gao et al.
NeurIPS'23	SFGC	Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data	Xin Zheng et al.	[code]
Arxiv'23	GroC	Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training	Xinglin Li et al.
Arxiv'24	CTRL	Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching	Tianle Zhang et al.	[code]
ICML'24	GEOM	Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching	Yuchen Zhang et al.	[code]
KDD'24	GCSR	Graph Data Condensation via Self-expressive Graph Structure Reconstruction	Zhanyu Liu et al.	[code]
Arxiv'24	TinyGraph	TinyGraph: Joint Feature and Node Condensation for Graph Neural Networks	Yezi Liu et al.
KDD'24	SGDC	Self-Supervised Learning for Graph Dataset Condensation	Yuxiang Wang et al.	[code]
ECCV'24	GSTAM	GSTAM: Efficient Graph Distillation with Structural Attention-Matching	Arash Rasti-Meymandi et al.	[code]
Arxiv'25	HyDRO	Random Walk Guided Hyperbolic Graph Distillation	Yunbo Long et al.

Efficient Graph Condensation

KDD'22	DosCond	Condensing Graphs via One-Step Gradient Matching	Wei Jin et al.	[code]
Arxiv'22	GCDM	Graph Condensation via Receptive Field Distribution Matching	Mengyang Liu et al.
KDD'23	KIDD	Kernel Ridge Regression-Based Graph Dataset Distillation	Zhe Xu et al.	[code]
WWW'24	GC-SNTK	Fast Graph Condensation with Structure-based Neural Tangent Kernel	Lin Wang et al.
ICLR'24	Mirage	Mirage: Model-Agnostic Graph Distillation for Graph Classification	Mridul Gupta et al.	[code]
Arxiv'24	DisCo	Disentangled Condensation for Large-scale Graphs	Zhenbang Xiao et al.	[code]
WWW'24	EXGC	EXGC: Bridging Efficiency and Explainability in Graph Condensation	Junfeng Fang et al.	[code]
Arxiv'24	SimGC	Simple Graph Condensation	Zhenbang Xiao et al.	[code]
WWW'25	CGC	Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition	Xinyi Gao et al.	[code]
Arxiv'25	GCGP	Efficient Graph Condensation via Gaussian Process	Lin Wang et al.	[code]
Arxiv'25	GECC	Scalable Graph Condensation with Evolving Capabilities	Shengbo Gong et al.

Generalized Graph Condensation

NeurIPS'23	SGDD	Does Graph Distillation See Like Vision Dataset Counterpart?	Beining Yang et al.	[code]
ICML'24	GDEM	Graph Distillation with Eigenbasis Matching	Yang Liu et al.
KDD'24	OpenGC	Graph Condensation for Open-World Graph Learning	Xinyi Gao et al.
Arxiv'24	CTGC	Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learning	Xinyi Gao et al.

Fair Graph Condensation

NeurIPS'23	FGD	Fair Graph Distillation	Qizhang Feng et al.
AS'23	GCARe	GCARe: Mitigating Subgroup Unfairness in Graph Condensation through Adversarial Regularization	Runze Mao et al.

Robust Graph Condensation

Arxiv'24	RobGC	RobGC: Towards Robust Graph Condensation	Xinyi Gao et al.

---

 

Applications

Graph Continual Learning

ICDM'23	CaT	CaT: Balanced Continual Graph Learning with Graph Condensation	Yilun Liu et al.	[code]
Arxiv'23	PUMA	PUMA: Efficient Continual Graph Learning with Graph Condensation	Yilun Liu et al.	[code]

Hyper-Parameter/Neural Architecture Search

Arxiv'23	HCDC	Faster Hyperparameter Search for GNNs via Calibrated Dataset Condensation	Mucong Ding et al.

Federated Learning

Arxiv'23	FedGKD	FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks	Qiying Pan et al.
Arxiv'24	FedGC	Federated Graph Condensation with Information Bottleneck Principles	Bo Yan

Inference Acceleration

ICDE'24	MCond	Graph Condensation for Inductive Node Representation Learning	Xinyi Gao et al.

Heterogeneous Graph

TKDE'24	HGCond	Heterogeneous Graph Condensation	Jian Gao et al.	[code]
ICDE'25	FreeHGC	Training-free Heterogeneous Graph Condensation via Data Selection	Yuxuan Liang et al.	[code]

Hypergraph Graph

WWW'25	HG-Cond	Exploring Hypergraph Condensation via Variational Hyperedge Generation and Multi-Aspectual Amelioration	Zheng Gong et al.

Security

Arxiv'24	BGC	Backdoor Graph Condensation	Jiahao Wu et al.
Arxiv'25	GraphDART	GraphDART: Graph Distillation for Efficient Advanced Persistent Threat Detection	Saba Fathi Rabooki et al.

---

 

Open-Source Libraries

Library	Paper	Implementation	#GC Methods	#Datasets	Tasks
GCondenser	[paper]	PyG, DGL	6	7	Node classification
GC-Bench	[paper]	PyG	9	12	Node classification, graph classification, link prediction, node clustering, anomaly detection
GraphSlim	[paper]	PyG	7	5	Node classification

---

 

Related Repositories

In addition to this Graph Condensation Papers Repository, you may find the following related repositories valuable for your research and exploration:

• Awesome-graph-reduction
• Awesome-Graph-Condensation
• Awesome-Dataset-Distillation

---

 

Contact

For any inquiries or suggestions regarding this repository, please don't hesitate to contact us by opening an issue on this repository.

Thank you for your interest in the Graph Condensation Papers Repository. We hope you find it valuable for your research and exploration. If you find this repository to be useful, please cite our survey paper.

@article{gao2024graph,
 title={Graph condensation: A survey},
 author={Gao, Xinyi and Yu, Junliang and Chen, Tong and Ye, Guanhua and Zhang, Wentao and Yin, Hongzhi},
 journal={arXiv preprint arXiv:2401.11720},
 year={2024}
}