Home

Awesome

awesome-graph-reduction

PRs Welcome Awesome Stars

[IJCAI 2024] This is a curated list of papers about graph reduction including graph condensation, graph coarsening, graph sparsification, graph summarization, etc.

If you want to add new entries, please make PRs with the same format.

This list serves as a complement to the survey below.

imageimageimage[A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation]

<div align=center><img src="https://github.com/ChandlerBang/awesome-graph-reduction/blob/main/figs/graph_reduction.png" width="500" /></div>

If you find this repo helpful, we would appreciate it if you could cite our survey.

@article{hashemi2024comprehensive,
  title={A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation},
  author={Hashemi, Mohammad and Gong, Shengbo and Ni, Juntong and Fan, Wenqi and Prakash, B Aditya and Jin, Wei},
  journal={International Joint Conference on Artificial Intelligence (IJCAI)},
  year={2024}
}

Graph Condensation / Graph Dataset Distillation

<!--#### Applications - [ICDM 2023] CaT: Balanced Continual Graph Learning with Graph Condensation. [[pdf]](https://arxiv.org/pdf/2309.09455.pdf) [[code]](https://github.com/superallen13/CaT-CGL) - [arXiv 2023] FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks. [[pdf]](https://arxiv.org/pdf/2309.09517.pdf) -->

Graph Coarsening / Clustering / Summary

GNN-involved

non-GNN-involved

<!-- - [ICLR 2018] FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling. [[pdf]](https://arxiv.org/pdf/1801.10247.pdf) [[code]](https://github.com/matenure/FastGCN) - [ICML 2018] Stochastic Training of Graph Convolutional Networks with Variance Reduction. [[pdf]](https://arxiv.org/pdf/1710.10568.pdf) [[code]](https://github.com/thu-ml/stochastic_gcn)--> <!-- - [IJCAI 2023] Gapformer: Graph Transformer with Graph Pooling for Node Classification. [[pdf]](https://www.ijcai.org/proceedings/2023/0244.pdf) - [NeurIPS 2022] Hierarchical graph transformer with adaptive node sampling. [[pdf]](https://arxiv.org/pdf/2210.03930.pdf)-->

Graph Sparsification / Sampling / Selection

GNN-involved

<!-- - [arXiv 2024] Two Heads Are Better Than One:Boosting Graph Sparse Training via Semantic and Topological Awareness. [[pdf]](https://arxiv.org/pdf/2402.01242.pdf) [[code]](https://anonymous.4open.science/r/GST-0F15) - [TPAMI 2023] Graph Neural Network Meets Sparse Representation: Graph Sparse Neural Networks via Exclusive Group Lasso. [[pdf]](https://ieeexplore.ieee.org/document/10149528)-->

non-GNN-involved

<!-- - - [ICLR 2020] DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. [[pdf]](https://arxiv.org/pdf/1907.10903.pdf) [[code]](https://github.com/DropEdge/DropEdge) [WSDM 2021] Learning to Drop: Robust Graph Neural Network via Topological Denoising. [[pdf]](https://arxiv.org/pdf/2011.07057.pdf) [[code]](https://github.com/flyingdoog/PTDNet)-->

Surveys & Benchmarks

Graph Reduction/ Summarization / Simplification

Other related topics

Toolkits