└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Awesome-Graph-Structure-Learning 2 | ![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg) 3 | > A collection of papers on **Graph Structural Learning (GSL)**. We will try to make this list updated frequently. If you found any error or any missed paper, please don't hesitate to open issues or pull requests. 4 | > 5 | > We have developed a comprehensive graph structure learning benchmark ([GSLB](https://github.com/GSL-Benchmark/GSLB)), which consists of diverse graph datasets and state-of-the-art GSL algorithm. Feel free to explore our benchmark and provide any feedback or contributions. 6 | 7 | 8 | 9 | 2024 10 | ---- 11 | * [NeurIPS 2024] **Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning** [[Paper](https://arxiv.org/abs/2409.17386) | [Code](https://github.com/zxlearningdeep/InfoMGF/tree/main/InfoMGF)] 12 | * [TKDE 2024] **Bi-Level Graph Structure Learning for Next POI Recommendation** [[Paper](https://ieeexplore.ieee.org/abstract/document/10521856)] 13 | * [ICDE 2024] **Learning Time-aware Graph Structures for Spatially Correlated Time Series Forecasting** [[Paper](https://arxiv.org/pdf/2312.16403)] 14 | * [ACL 2024] **S2GSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis** [[Paper](https://arxiv.org/abs/2406.02902) | [Code](https://github.com/ouy7han/S2GSL)] 15 | * [WWW 2024] **DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning** [[Paper](https://arxiv.org/abs/2402.13711) | [Code](https://github.com/seungyoon-Choi/DSLR_official)] 16 | * [WWW 2024] **Self-Guided Robust Graph Structure Refinement** [[Paper](https://arxiv.org/abs/2402.11837) | [Code](https://github.com/yeonjun-in/torch-SG-GSR)] 17 | * [AAAI 2024] **Neural Gaussian Similarity Modeling for Differential Graph Structure Learning** [[Paper](https://arxiv.org/abs/2312.09498)] 18 | 19 | 2023 20 | ---- 21 | * [NeurIPS 2023] **Latent Graph Inference with Limited Supervision** [[Paper](https://arxiv.org/abs/2310.04314) | [Code](https://github.com/Jianglin954/LGI-LS)] 22 | * [NeurIPS 2023] **Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First** [[Paper](https://arxiv.org/abs/2310.18735) | [Code](https://github.com/rollingstonezz/Curriculum_learning_for_GNNs)] 23 | * [NeurIPS 2023] **Towards Label Position Bias in Graph Neural Networks** [[Paper](https://arxiv.org/abs/2305.15822)] 24 | * [ICDE 2023] **Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting** [[Paper](https://arxiv.org/abs/2309.12028)] 25 | * [CIKM 2023] **Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphs** [[Paper](https://dl.acm.org/doi/10.1145/3583780.3615081) | [Code](https://github.com/ViktorAxelsen/TGSL)] 26 | * [CIKM 2023] **RDGSL: Dynamic Graph Representation Learning with Structure Learning** [[Paper](https://arxiv.org/abs/2309.02025)] 27 | * [CIKM 2023] **Homophily-enhanced Structure Learning for Graph Clustering** [[Paper](https://arxiv.org/abs/2308.05309) | [Code](https://github.com/galogm/HoLe)] 28 | * [IJCAI 2023] **Beyond Homophily: Robust Graph Anomaly Detection via Neural Sparsification** [[Paper](https://www.ijcai.org/proceedings/2023/0234.pdf) | [Code](https://github.com/KellyGong/SparseGAD)] 29 | * [KDD 2023] **PROSE: Graph Structure Learning via Progressive Strategy** [[Paper](https://dl.acm.org/doi/10.1145/3580305.3599476) | [Code](https://github.com/tigerbunny2023/PROSE)] 30 | * [KDD 2023] **Transferable Graph Structure Learning for Graph-based Traffic Forecasting Across Cities** [[Paper](https://kl4805.github.io/files/KDD23.pdf) | [Code](https://github.com/KL4805/TransGTR/)] 31 | * [KDD 2023] **GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks** [[Paper](https://arxiv.org/abs/2306.11264) | [Code](https://github.com/WtaoZhao/GraphGLOW)] 32 | * [TNNLS 2023] **Homophily-Enhanced Self-Supervision for Graph Structure Learning: Insights and Directions** [[Paper](https://ieeexplore.ieee.org/abstract/document/10106110) | [Code](https://github.com/LirongWu/Homophily-Enhanced-Self-supervision)] 33 | * [WWW 2023] **Homophily-oriented Heterogeneous Graph Rewiring** [[Paper](http://arxiv.org/abs/2302.06299)] 34 | * [WWW 2023] **SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization** [[Paper](https://arxiv.org/abs/2303.09778) | [Code](https://github.com/RingBDStack/SE-GSL)] 35 | * [ICDE 2023] **Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transport** [[Paper](https://arxiv.org/abs/2301.12721) | [Code](https://github.com/squareRoot3/SLOTAlign)] 36 | * [WSDM 2023] **Self-Supervised Graph Structure Refinement for Graph Neural Networks** [[Paper](https://dl.acm.org/doi/abs/10.1145/3539597.3570455) | [Code](https://github.com/andyjzhao/WSDM23-GSR)] 37 | * [AAAI 2023] **Directed Acyclic Graph Structure Learning from Dynamic Graphs** [[Paper](http://www.shichuan.org/doc/142.pdf) | [Code](https://github.com/BUPT-GAMMA/GraphNOTEARS)] 38 | * [AAAI 2023] **Self-organization Preserved Graph Structure Learning with Principle of Relevant Information** [[Paper](https://arxiv.org/abs/2301.00015) ｜ [Code](https://github.com/RingBDStack/PRI-GSL)] 39 | * [AAAI 2023] **USER: Unsupervised Structural Entropy-based Robust Graph Neural Network** [[Paper](https://arxiv.org/abs/2302.05889) | [Code](https://github.com/wangyifeibeijing/USER)] 40 | * [AAAI 2023] **Spatio-Temporal Meta-Graph Learning for Traffic Forecasting** [[Paper](https://arxiv.org/abs/2211.14701) | [Code](https://github.com/deepkashiwa20/MegaCRN)] 41 | * [TPAMI 2023] **Differentiable Graph Module (DGM) for Graph Convolutional Networks** [[Paper](https://ieeexplore.ieee.org/document/9763421) | [Code](https://github.com/lcosmo/DGM_pytorch)] 42 | 43 | 2022 44 | ---- 45 | * [TNNLS 2022] **Reverse graph learning for graph neural network** [[Paper](https://ieeexplore.ieee.org/abstract/document/9749776)] 46 | * [NeurIPS 2022] **Contrastive Graph Structure Learning via Information Bottleneck for Recommendation** [[Paper](https://openreview.net/forum?id=lhl_rYNdiH6) | [Code](https://github.com/weicy15/CGI)] 47 | * [NeurIPS 2022] **NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification** [[Paper](https://openreview.net/forum?id=sMezXGG5So) | [Code](https://github.com/qitianwu/NodeFormer)] 48 | * [NeurIPS 2022] **Simultaneous Missing Value Imputation and Structure Learning with Groups** [[Paper](https://arxiv.org/abs/2110.08223) | [Code](https://github.com/microsoft/causica)] 49 | * [CIKM 2022] **Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing** [[Paper](https://dl.acm.org/doi/abs/10.1145/3511808.3557419) | [Code](https://github.com/RingBDStack/PASTEL)] 50 | * [KDD 2022] **Towards an Optimal Asymmetric Graph Structure for Robust Semi-supervised Node Classification** [[Paper](https://dl.acm.org/doi/abs/10.1145/3534678.3539332)] 51 | * [KDD 2022] **Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN** [[Paper](https://dl.acm.org/doi/abs/10.1145/3534678.3539484) | [Code](https://github.com/likuanppd/STABLE)] 52 | * [ICML 2022] **Boosting graph structure learning with dummy nodes** [[Paper](https://proceedings.mlr.press/v162/liu22d.html) | [Code](https://github.com/HKUST-KnowComp/DummyNode4GraphLearning)] 53 | * [WWW 2022] **Towards Unsupervised Deep Graph Structure Learning** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3485447.3512186?casa_token=445ECOqpVh4AAAAA:3ZBlGDSLFxrhwN0zEUdGFMpB4DslsI4h-rFLvI3cWHNzNsx6k-4m2t-NiDLubRvw1tBLaziISw) | [Note](https://zepengzhang.com/Notes/2022/20220512.pdf) | [Code](https://github.com/GRAND-Lab/SUBLIME)] 54 | * [WWW 2022] **Compact Graph Structure Learning via Mutual Information Compression** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3485447.3512206?casa_token=lyWPk8kyFzwAAAAA:HLmbgpzrKe17LbnQqNh2zI_6WOvNgm_VqfNAgEoqLSXR7rRm_Bzro1oNzETTQb63W9vcVlijNw) | [Code](https://github.com/liun-online/CoGSL)] 55 | * [WWW 2022] **Prohibited Item Detection via Risk Graph Structure Learning** [[Paper](https://dl.acm.org/doi/10.1145/3485447.3512190)] 56 | * [WSDM 2022] **Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels** [[Paper](https://dl.acm.org/doi/10.1145/3488560.3498408) | [Code](https://github.com/EnyanDai/RSGNN)] 57 | * [AAAI 2022] **GPN: A Joint Structural Learning Framework for Graph Neural Networks** [[Paper](https://arxiv.org/abs/2205.05964)] 58 | * [AAAI 2022] **Graph Structure Learning with Variational Information Bottleneck** [[Paper](https://ojs.aaai.org/index.php/AAAI/article/view/20335) | [Code](https://github.com/RingBDStack/VIB-GSL)] 59 | * [arXiv 2022] **GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks** [[Paper](https://arxiv.org/pdf/2201.12741.pdf) | [Note](https://zepengzhang.com/Notes/2022/20220617.pdf)] 60 | * [IJCAI 2022] **Hypergraph Structure Learning for Hypergraph Neural Networks** [[Paper](https://www.ijcai.org/Proceedings/2022/267)] 61 | * [IJCAI 2022] **Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting** [[Paper](https://www.ijcai.org/Proceedings/2022/328) | [Code](https://github.com/alipay/RGSL)] 62 | * [ICLR 2022] **Understanding over-squashing and bottlenecks on graphs via curvature** [[Paper](https://arxiv.org/abs/2111.14522)] 63 | * [arXiv 2022] **A Survey on Graph Structure Learning: Progress and Opportunities** [[Paper](https://sxkdz.github.io/files/publications/IJCAI/GSL.pdf)] 64 | 65 | 2021 66 | ---- 67 | * [NeurIPS 2021] **SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks** [[Paper](https://proceedings.neurips.cc/paper/2021/file/bf499a12e998d178afd964adf64a60cb-Paper.pdf) | [Note](https://zepengzhang.com/Notes/2022/20220507.pdf) | [Code](https://github.com/BorealisAI/SLAPS-GNN)] 68 | * [WWW 2021] **Graph Structure Estimation Neural Networks** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3442381.3449952?casa_token=Ac8pftvrgv0AAAAA:Ka_mklQVpQmYfhNVB-r66cf6fFsCdy8jyVKGFvzC1q5Ko5DbQQqci_3vopigN0jzTDlWiL8L8Q) | [Code](https://github.com/BUPT-GAMMA/Graph-Structure-Estimation-Neural-Networks)] 69 | * [CIKM 2021] **Speedup Robust Graph Structure Learning with Low-Rank Information** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3459637.3482299?casa_token=Wm1gGo5XvoUAAAAA:YOnSmTKmVxGWoxzQSuHZ6522cSdKLq3yJpaVp1kCtuvtXtxLcyk6qA_E8uGuevH0sJjUsVCbsQ)] 70 | * [WSDM 2021] **Learning to Drop: Robust Graph Neural Network via Topological Denoising** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3437963.3441734) | [Note](https://zepengzhang.com/Notes/2022/20220611.pdf) | [Code](https://github.com/flyingdoog/PTDNet)] 71 | * [WSDM 2021] **Node Similarity Preserving Graph Convolutional Networks** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3437963.3441735) | [Code](https://github.com/ChandlerBang/SimP-GCN)] 72 | * [IJCAI 2021] **Understanding Structural Vulnerability in Graph Convolutional Networks** [[Paper](https://arxiv.org/pdf/2108.06280.pdf) | [Code](https://github.com/EdisonLeeeee/MedianGCN)] 73 | * [ECML-PKDD 2021] **Graph-Revised Convolutional Network** [[Paper](https://arxiv.org/pdf/1911.07123.pdf) | [Note](https://zepengzhang.com/Notes/2022/20220605.pdf) | [Code](https://github.com/PlusRoss/GRCN)] 74 | * [arXiv 2021] **A General Unified Graph Neural Network Framework Against Adversarial Attacks** [[Paper](https://openreview.net/pdf?id=bpUHBc9HCU8)] 75 | * [AAAI 2021] **Heterogeneous Graph Structure Learning for Graph Neural Networks** [[Paper](https://ojs.aaai.org/index.php/AAAI/article/view/16600) | [Code](https://github.com/AndyJZhao/HGSL)] 76 | * [ICLR 2021] **Discrete Graph Structure Learning for Forecasting Multiple Time Series** [[Paper](https://openreview.net/pdf?id=WEHSlH5mOk) | [Code](https://github.com/chaoshangcs/GTS)] 77 | * [IoTJ 2021] **Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT** [[Paper](https://arxiv.org/pdf/2104.03466.pdf) | [Code](https://github.com/zackchen-lb/GTA)] 78 | 79 | 2020 80 | ---- 81 | * [TNNLS 2020] **Probabilistic semi-supervised learning via sparse graph structure learning** [[Paper](https://ieeexplore.ieee.org/abstract/document/9063663)] 82 | * [ICML 2020] **Robust Graph Representation Learning via Neural Sparsification** [[Paper](http://proceedings.mlr.press/v119/zheng20d/zheng20d.pdf) | [Code](https://github.com/flyingdoog/PTDNet)] 83 | * [NeurIPS 2020] **Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings** [[Paper](https://proceedings.neurips.cc/paper/2020/file/e05c7ba4e087beea9410929698dc41a6-Paper.pdf) | [Note](https://zepengzhang.com/Notes/2022/20220513.pdf) | [Code](https://github.com/hugochan/IDGL)] 84 | * [NeurIPS 2020] **GNNGUARD: Defending Graph Neural Networks against Adversarial Attacks** [[Paper](https://proceedings.neurips.cc/paper/2020/file/690d83983a63aa1818423fd6edd3bfdb-Paper.pdf)] 85 | * [NeurIPS 2020] **Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting** [[Paper](https://proceedings.neurips.cc/paper/2020/file/ce1aad92b939420fc17005e5461e6f48-Paper.pdf) | [Code](https://github.com/LeiBAI/AGCRN)] 86 | * [KDD 2020] **Graph Structure Learning for Robust Graph Neural Networks** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3394486.3403049) | [Code](https://github.com/ChandlerBang/Pro-GNN)] 87 | * [KDD 2020] **Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks** [[Paper](https://dl.acm.org/doi/10.1145/3394486.3403118) |[Code](https://github.com/nnzhan/MTGNN)] 88 | * [WSDM 2020] **All You Need Is Low (Rank): Defending Against Adversarial Attacks on Graphs** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3336191.3371789) | [Note](https://zepengzhang.com/Notes/2022/20220621.pdf)] 89 | * [ICDM 2020] **Provably Robust Node Classification via Low-Pass Message Passing** [[Paper](https://shenghua-liu.github.io/papers/icdm2020-provablerobust.pdf)] 90 | * [CIKM 2020] **Data Augmentation for Graph Classification** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3340531.3412086) | [Code](https://github.com/zhao-tong/GAug)] 91 | 92 | Before 2020 93 | ---- 94 | * [ICML 2019] **Learning Discrete Structures for Graph Neural Networks** [[Paper](http://proceedings.mlr.press/v97/franceschi19a/franceschi19a.pdf) | [Note](https://zepengzhang.com/Notes/2022/20220620.pdf) | [Code](https://github.com/lucfra/LDS-GNN)] 95 | * [KDD 2018] **Adversarial Attacks on Neural Networks for Graph Data** [[Paper](https://dl.acm.org/doi/pdf/10.1145/3219819.3220078?casa_token=NvByIo5CJcYAAAAA:mgvVVbv3KA0HWJpo_c5af36QBFfqSZBhTfZsGabdJ226UFEFqHK03JX-3yTAb8eULfUbop2Kjw) | [Code](https://github.com/danielzuegner/nettack)] 96 | * [ICDM 2019] **Learning Robust Representations with Graph Denoising Policy Network** [[Paper](https://arxiv.org/pdf/1910.01784.pdf)] 97 | * [IJCAI 2019] **Adversarial Examples for Graph Data: Deep Insights into Attack and Defense** [[Paper](https://arxiv.org/pdf/1903.01610.pdf)] 98 | * [CVPR 2019] **Semi-supervised Learning with Graph Learning-Convolutional Networks** [[Paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Jiang_Semi-Supervised_Learning_With_Graph_Learning-Convolutional_Networks_CVPR_2019_paper.pdf)] 99 | * [AAAI 2018] **Adaptive Graph Convolutional Neural Networks** [[Paper](https://ojs.aaai.org/index.php/AAAI/article/view/11691)] 100 | * [ICML 2018] **Neural Relational Inference for Interacting Systems** [[Paper](http://proceedings.mlr.press/v80/kipf18a/kipf18a.pdf) | [Code](https://github.com/ethanfetaya/nri)] 101 | 102 | ## Contributing 103 | If you have come across relevant resources, feel free to open an issue or submit a pull request. 104 | 105 | ```* [conference] **paper_name** [[Paper](link) | [Code](link)]``` 106 | --------------------------------------------------------------------------------