文件列表:

.idea/ (0, 2023-10-31)
.idea/Awesome-Data-Centric-GraphML.iml (284, 2023-10-31)
.idea/inspectionProfiles/ (0, 2023-10-31)
.idea/inspectionProfiles/profiles_settings.xml (174, 2023-10-31)
.idea/misc.xml (185, 2023-10-31)
.idea/modules.xml (308, 2023-10-31)
.idea/vcs.xml (241, 2023-10-31)
ADC2023/ (0, 2023-10-31)
ADC2023/DC-GML_tutorial_final.pdf (15689360, 2023-10-31)
LICENSE (1075, 2023-10-31)

# Awesome-Data-Centric-GraphML A collection of papers and resources about Data-centric Graph Machine Learning (DC-GML). We undertake a comprehensive **review** and provide a promising **outlook** for data-centric graph machine learning (DC-GML), and propose a systematic framework for DC-GML that encompasses all stages of the graph data lifecycle, including graph data collection, exploration, improvement, exploitation, and maintenance. More details can be found in our review & outlook work: https://arxiv.org/abs/2309.10979 ``` @article{zheng2023towards, title={Towards Data-centric Graph Machine Learning: Review and Outlook}, author={Zheng, Xin and Liu, Yixin and Bao, Zhifeng and Fang, Meng and Hu, Xia and Liew, Alan Wee-Chung and Pan, Shirui}, journal={arXiv preprint arXiv:2309.10979}, year={2023}} ``` ## Updates - **2023.11** - Invited to give a tutorial in Australia Database Conference (ADC), 2023. The tutorial slides can be found in the folder. Table of Contents ================= * [Awesome-Data-Centric-GraphML](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#awesome-data-centric-graphml) * [How To Enhance Graph Data Availability and Quality?](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#how-to-enhance-graph-data-availability-and-quality) * [Graph Structure Enhancement](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-structure-enhancement) * [Graph Structure Learning](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-structure-learning) * [Graph Sparsification](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-sparsification) * [Graph Diffusion](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-diffusion) * [Graph Feature Enhancement](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-feature-enhancement) * [Graph Feature Completion](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-feature-completion) * [Graph Feature Denoising](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-feature-denoising) * [Graph Label Enhancement](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-label-enhancement) * [Graph Pseudo-labeling](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-pseudo-labeling) * [Graph Label Denoising](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-label-denoising) * [Graph Class-imbalanced Sampling](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-class-imbalanced-sampling) * [Graph Size Enhancement](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-size-enhancement) * [Graph Size Reduction](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-size-reduction) * [Graph Data Augmentation](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-data-augmentation) * [How To Learn From Graph Data With Limited-availability and Low-quality?](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#how-to-learn-from-graph-data-with-limited-availability-and-low-quality) * [Graph Self-supervised Learning](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-self-supervised-learning) * [Graph Semi-supervised Learning](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-semi-supervised-learning) * [Graph Active Learning](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-active-learning) * [Graph Transfer Learning](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-transfer-learning) * [How To Build Graph MLOps System: The Graph Data-centric View.](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#how-to-build-graph-mlops-system-the-graph-data-centric-view) * [Graph Data Collection](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-data-collection) * [Graph Data Exploration](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-data-exploration) * [Graph Data Maintenance](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-data-maintenance) * [Graph MLOps](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/#graph-mlops) ## How To Enhance Graph Data Availability and Quality? The answer to this question corresponds to **'Graph Data Improvement'** stage in DC-GML framework, incorporating four aspects of graph data characteristics, i.e., *Graph Structure Enhancement, Graph Feature Enhancement, Graph Label Enhancement, and Graph Size Enhancement*. ### Graph Structure Enhancement #### Graph Structure Learning - [KDD'2020-Pro-GNN] Graph structure learning for robust graph neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3394486.3403049) - [ICML'2019-LDS] Learning discrete structures for graph neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/http://proceedings.mlr.press/v97/franceschi19a/franceschi19a.pdf) - [WWW'2021-GEN] Graph structure estimation neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3442381.3449952?casa_token=WBEXRhs6I_YAAAAA:cVk3EONP8EwXVzuUSZp8Qp-gZOLEVJYHDLV-hXTJ-gh5v-I_LuTYfvxKlk_Y5rOUfFKYZW9ty5xKg1w) - [CVPR'2019-GLCN] Semi-supervised learning with graph learning convolutional networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/http://openaccess.thecvf.com/content_CVPR_2019/papers/Jiang_Semi-Supervised_Learning_With_Graph_Learning-Convolutional_Networks_CVPR_2019_paper.pdf) - [NIPS'2020-IDGL] Iterative deep graph learning for graph neural networks: Better and robust node embeddings. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.neurips.cc/paper/2020/file/e05c7ba4e087beea9410929698dc41a6-Paper.pdf) #### Graph Sparsification - [AIS'2016] Graph sparsification approaches for laplacian smoothing. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/http://proceedings.mlr.press/v51/sadhanala16.pdf) - [SIGMOD'2011] Local graph sparsification for scalable clustering. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/1989323.1989399?casa_token=_CYKRbVjXTcAAAAA:WGIgqzcngwWBBkw9of3Wbjrc8JES8cAw39VQKKkTlVzB_MA_IQoCDyTd7rLe_1609i0wVXIPt8O3dpY) - [SICOMP'2011] Spectral sparsification of graphs.[[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/0808.4134) - [NIPS'2019] On differentially private graph sparsification and applications. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.neurips.cc/paper/2019/file/e44e875c12109e4fa3716c05008048b2-Paper.pdf) - [ICDM'2022-GraphSparsify] A generic graph sparsification framework using deep reinforcement learning. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ieeexplore.ieee.org/iel7/10027565/10027596/10027736.pdf?casa_token=ST116wBmpbMAAAAA:jfGOFwHoX4AsOiSUQYYNV6BUuC_mUKaPG5aKVTvSzK0PkJulHXAYk-Is9MzRSLISUhHZnQlIaEDN) #### Graph Diffusion - [ICLR'2019-PPNP/APPNP] Predict then propagate: graph neural networks meet personalized pagerank. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/1810.05997) - [NIPS'2019-GDC] Diffusion improves graph learning. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.neurips.cc/paper/2019/file/23c894276a2c5a16470e6a31f4618d73-Paper.pdf) - [ICLR'2021] Adaptive universal generalized pagerank graph neural network. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/2006.07988) - [NIPS'2021-ADC] Adaptive diffusion in graph neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.neurips.cc/paper/2021/file/c42af2fa7356818e0389593714f59b52-Paper.pdf) ### Graph Feature Enhancement #### Graph Feature Completion - [NN'2020-GINN] Missing data imputation with adversarially-trained graph convolutional networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://www.sciencedirect.com/science/article/pii/S0893608020302185?casa_token=I7BtgyazKl8AAAAA:edsPKQbKSp1fbciuDc76aYnSPSS6T03ESUb_i2KDUJ6o2cA5LVCS-K8SfkhgWCqi5Bqog9hihvU) - [FGCS'2021-GCN_MF] Graph convolutional networks for graphs containing missing features. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://www.sciencedirect.com/science/article/pii/S0167739X20330405) - [TPAMI'2020-SAT] Learning on attribute-missing graphs. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ieeexplore.ieee.org/iel7/34/4359286/09229522.pdf?casa_token=TsPVGT_mK-AAAAAA:XJ-eH3DCQ5OnkXvj5UhHBb8IC8O_I3WyworEudS9D2c-E7usbAovpaNswysThFSCPWWq94Az9EU-) - [WWW'2021-HGNN-AC] Heterogeneous graph neural network via attribute completion. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3442381.3449914?casa_token=N3XrnbFD-VsAAAAA:aJnfUQvXnC-7T2INzKCmo3kLYGa1qJ1Z_EgTPH5gSRblwPFvlUCxg1sXgmnOcBSRLR-VuE6_Cv-DLM8) - [IEEETransCybern'2022-Amer] Amer: A new attribute-missing network embedding approach. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ieeexplore.ieee.org/iel7/6221036/6352949/09765782.pdf?casa_token=TNBxp_Z_qf8AAAAA:VPKCn0964kuE4tJZPTvUG1xAP2MEy_QvA0ym6ry8Cvu28BuFqUkG2P9xYGmXDx13TUvC_6NBu5V1) - [arxiv'2021-SAGA] Siamese attribute-missing graph auto-encoder. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/2112.04842) #### Graph Feature Denoising - [SPM'2013] The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ieeexplore.ieee.org/iel7/79/6494646/06494675.pdf?casa_token=mD3rZmt2imAAAAAA:dtVEN95FqjgPHlO9pQ_c-xTtDMPuknx3pdjPVIkffAMEkoCRW-26vAq8gbjlXCh1Q02tEUbPHg) - [GlobalSIP'2014] Signal denoising on graphs via graph filtering. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ieeexplore.ieee.org/iel7/7010655/7032060/07032244.pdf?casa_token=EyFQK1dNZTUAAAAA:wzIP7ZxTWQQHcy4pfRmk3_JrDv39r8VyIXueZ_Y25VVeXHixoOP0mIMckQAn2prDBZO6EnfpFM8P) - [IET-SP'2018] Graph polynomial filter for signal denoising. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://scholar.google.com/scholar?output=instlink&q=info:N5LbqcYw_6AJ:scholar.google.com/&hl=zh-CN&as_sdt=0,5&scillfp=17975566870893489622&oi=lle) - [AIS'2015] Trend filtering on graphs. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/http://proceedings.mlr.press/v38/wang15d.pdf) - [ICASSP'2020] Graph auto-encoder for graph signal denoising. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ieeexplore.ieee.org/iel7/9040208/9052899/09053623.pdf?casa_token=wp6nKhBq4eQAAAAA:VbeeBWniW1nbGLsSSTDaOlUt8Co50jVEejxpZQziCDzx8NnIJ_0ZPGVdJNi5GG9pRKAaA-rENrOL) - [TSP'2021] Graph unrolling networks: Interpretable neural networks for graph signal denoising. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ieeexplore.ieee.org/iel7/78/4359509/09453145.pdf?casa_token=WBFBG92sg-wAAAAA:CFc6t1fhHyEQleL3nCQiBE5XNjTGFqS80VXxkHSDPEPzS7OEed6ydOV7M0ZN-yKlrkljWt-sXKh7) - [TSP'2022] Untrained graph neural networks for denoising. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ieeexplore.ieee.org/iel7/78/4359509/09959969.pdf?casa_token=79riV29MxvkAAAAA:kEUgypSxBhsj1TqD-3vTPxUY1JoHN5E6vTh2uFkuJrSTiA7bGt6qIorsfuHB3kxczHZGkyH8E0Um) - [WWW'2023-MAGNET] Robust graph representation learning for local corruption recovery. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://yuguangwang.github.io/papers/L_p_graph_regularizer_ICML%20TAG%202022.pdf) ### Graph Label Enhancement #### Graph Pseudo-labeling - [AAAI'2018] Deeper insights into graph convolutional networks for semi-supervised learning. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ojs.aaai.org/index.php/AAAI/article/view/11604/11463) - [AAAI'2020] Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ojs.aaai.org/index.php/AAAI/article/download/6048/5904) - [CIKM'2021-IFC-GCN] Rectifying pseudo labels: Iterative feature clustering for graph representation learning. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3459637.3482469?casa_token=j-229ROWIHwAAAAA:ubON8KC_ifOtZWU2MqrFg3ZAiloxu2JGcOWWSdIZcKj-qlfgeRzL0xclkB8DF6lxs_Qcmj1lz9UFTOo) - [arXiv'2019-DSGCN] Dynamic self-training framework for graph convolutional networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://openreview.net/pdf?id=SJgCEpVtvr) - [WSDM'2022-RS-GNN] Towards robust graph neural networks for noisy graphs with sparse labels. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3488560.3498408) - [DMKD'2023-InfoGNN] Informative pseudo-labeling for graph neural networks with few labels. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://link.springer.com/article/10.1007/s10618-022-00879-4) #### Graph Label Denoising - [WSDM'2023-CLNode] CLNode: Curriculum learning for node classification. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3539597.3570385?casa_token=cNDTalzkl6IAAAAA:0-d5yP4lt002LAiXl9dHRFQ7iARGawdtBSZ4rVR29UeBHabh8yC7YvjAJdAac3SKLutBKX_HrN1CNts) - [arXiv'2019-D-GNN] Learning graph neural networks with noisy labels. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/1905.01591) - [CIKM'2021-IFC-GCN] Rectifying pseudo labels: Iterative feature clustering for graph representation learning. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3459637.3482469?casa_token=j-229ROWIHwAAAAA:ubON8KC_ifOtZWU2MqrFg3ZAiloxu2JGcOWWSdIZcKj-qlfgeRzL0xclkB8DF6lxs_Qcmj1lz9UFTOo) - [KDD'2021-NRGNN] Nrgnn: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3447548.3467364) - [WSDM'2023-RTGNN] Robust training of graph neural networks via noise governance. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3539597.3570369?casa_token=9LQOlvbtC2AAAAAA:qmY_CT3ipOgGls6v5El4psDQ8tCMZpZfkRiSfBVAI32kXMTNkH2p9ZTQYLC2yUVoOjZJDEB5g27sEDo) #### Graph Class-imbalanced Sampling - [WSDM'2021-GraphSMOTE] Graphsmote: Imbalanced node classification on graphs with graph neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3437963.3441720) - [KDD'2021-ImGAGN] Imgagn: Imbalanced network embedding via generative adversarial graph networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3447548.3467334?casa_token=4G06vl98C9IAAAAA:YgtmaAMJO5uyHdy3XRNwiw9MQ-SwbVMNSC0M1FkVpbiw0n1XGkGkICXjl3urOfXVUDjsbjiwFWYhxOk) - [WWW'2021-PC-GNN] Pick and choose: a GNN-based imbalanced learning approach for fraud detection. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3442381.3449989) - [WWW'2021-GraphMixup] Mixup for node and graph classification. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3442381.3449796) - [ICLR'2021-GraphENS] GraphENS: Neighbor-aware ego network synthesis for class-imbalanced node classification. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://openreview.net/pdf?id=MXEl7i-iru) - [arXiv'2023-GraphSR] GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/2302.12814) - [NIPS'2021-ReNode] Topology-imbalance learning for semi-supervised node classification. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.neurips.cc/paper/2021/file/fa7cdfad1a5aaf8370ebeda47a1ff1c3-Paper.pdf) - [arXiv'2022-TopoImb] TopoImb: Toward topology-level imbalance in learning from graphs. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/2212.08689) - [IJCAI'2013-igBoost] Graph classification with imbalanced class distributions and noise. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://www.researchgate.net/profile/Shirui-Pan-3/publication/262204599_Graph_classification_with_imbalanced_class_distributions_and_noise/links/564bc59d08ae3374e5dddb5b/Graph-classification-with-imbalanced-class-distributions-and-noise.pdf) - [CIKM'2022-G2GNN] Imbalanced graph classification via graph-of-graph neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3511808.3557356?casa_token=gzP3pWpfsWMAAAAA:BPdp0A0Mh3tWlXo6i4Mvd5kfVo0geTqqfH_hOyCpAki9krAMdq6fZKCScHffiQdfq9mZSPYBRR85uL4) ### Graph Size Enhancement #### Graph Size Reduction - [ICML'2009-Herding] Herding dynamical weights to learn. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/1553374.1553517?casa_token=mSkkhW5jA84AAAAA:31mF183Hzi4X1un4BsuRLuaFVId7Febx4PXXQbbZ0uquebekHdDhncU3QhaH0zxb6ItnWYdWehkfhFM) - [CVPR'2017-ICARL] ICARL: Incremental classifier and representation learning. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://openaccess.thecvf.com/content_cvpr_2017/papers/Rebuffi_iCaRL_Incremental_Classifier_CVPR_2017_paper.pdf) - [ICLR'2018-K-center] Active learning for convolutional neural networks: A core-set approach. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/1708.00489.pdf) - [ICAIS'2020-Coarsening] Graph coarsening with preserved spectral properties. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/http://proceedings.mlr.press/v108/jin20a/jin20a.pdf) - [arXiv'2021] Graph domain adaptation: A generative view. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/2106.07482) - [ICLR'2021-GCond] Graph condensation for graph neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/2110.07580) - [KDD'2022-DosCond] Condensing graphs via one-step gradient matching. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3534678.3539429?casa_token=gijVmZummzYAAAAA:nq1yIq5wN-sLT-qsLavBYyys3163tZNUB_3Hj7bOC6bkE4wP5BHZEcf-faFnk5djxCujlvTLQ3BSnlc) - [NeurIPS-Workshop'2022] Faster hyperparameter search on graphs via calibrated dataset condensation. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://openreview.net/pdf?id=wcbgjg0X7LJ) - [arXiv'2023-SFGC] Structure-free graph condensation: From large-scale graphs to condensed graph-free data. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/2306.02664) #### Graph Data Augmentation - [ACM SIGKDD Explorations Newsletter'2022-Survey] Data augmentation for deep graph learning: A survey. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3575637.3575646?casa_token=RTnILzVw3x4AAAAA:la46qhiVu6kPiJ1k4dopSZTYb0iA4oo2r8sIEXSGUUkoTW5byrlx-9VVf5-OOkoc0cDfcC-GOYpzc2k) - [arXiv'2202-Survey] Graph data augmentation for graph machine learning: A survey. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/2202.08871) - [ICLR'2020-DropEdge] DropEdge: Towards deep graph convolutional networks on node classification. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/1907.10903) - [NeurIPS'2020-GRAND] Graph random neural networks for semi-supervised learning on graphs. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.neurips.cc/paper/2020/file/fb4c835feb0a65cc39739320d7a51c02-Paper.pdf) - [AAAI'2022-NASA] Regularizing graph neural networks via consistency-diversity graph augmentations. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ojs.aaai.org/index.php/AAAI/article/view/20307/20066) - [KDD'2020-NodeAug] NodeAug: Semi-supervised node classification with data augmentation. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3394486.3403063?casa_token=5O6rVP5WUNcAAAAA:39vUmeVOiby_U-6UC3f4_vw5YEox2awfj22tgTeoZMa8f2IPeQ0w-2x23QC8V9_nwSO2F8Y9tFVWUbY) - [AAAI'2021-GAUG] Data augmentation for graph neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ojs.aaai.org/index.php/AAAI/article/view/17315/17122) - [AAAI'2021-GraphMix] Graphmix: Improved training of gnns for semi-supervised learning. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ojs.aaai.org/index.php/AAAI/article/view/17203/17010) - [WWW'2021-GraphMixup] Mixup for node and graph classification. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3442381.3449796) - [WSDM'2021-GraphSMOTE] Graphsmote: Imbalanced node classification on graphs with graph neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3437963.3441720) - [CVPR'2022-FLAG] Robust optimization as data augmentation for large-scale graphs. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://openaccess.thecvf.com/content/CVPR2022/papers/Kong_Robust_Optimization_As_Data_Augmentation_for_Large-Scale_Graphs_CVPR_2022_paper.pdf) - [ICML'2022-G-Mixup] G-mixup: Graph data augmentation for graph classification. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.mlr.press/v162/han22c/han22c.pdf) - [ICML'2022-LAGNN] Local augmentation for graph neural networks. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.mlr.press/v162/liu22s/liu22s.pdf) ## How To Learn From Graph Data With Limited-availability and Low-quality? The answer to this question corresponds to **'Graph Data Exploitation'** stage in DC-GML framework, incorporating four strategies to learn from graph data with low-quality and limited-availability, i.e., *Graph Self-supervised Learning, Graph Semi-supervised Learning, Graph Active Learning, and Graph Transfer Learning*. ### Graph Self-supervised Learning - [TKDE'2022-Survey] Graph self-supervised learning: A survey. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://ieeexplore.ieee.org/iel7/69/10113816/09770382.pdf?casa_token=ydQeuh-OkpYAAAAA:hFnyLT6NKFztPKkO47dh8cdQ49fm5Sal8jmpoxdz5a4jBXqbL08A3miB1Z2XfGkrGChYovXRyb2W) - [arXiv'2016-GAE] Variational graph auto-encoders. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/1611.07308.pdf%5D) - [CIKM'2017-MGAE] MGAE: Marginalized graph autoencoder for graph clustering. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3132847.3132967?casa_token=JNQueyr_GKgAAAAA:7xzVsWp65NPw-I2MqMxV-OkI21tM6chr7nfSHdcihKJGaEL5IL3OFYD17uEXSCI4a4JS4wTFAsSshwI) - [IJCAI'2018-ARGA] Adversarially regularized graph autoencoder for graph embedding. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/1802.04407) - [ICLR'2019-DGI] Deep graph infomax. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/1809.10341) - [ICML'2020-MVGRL] Contrastive multi-view representation learning on graphs. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/http://proceedings.mlr.press/v119/hassani20a/hassani20a.pdf) - [NeurIPS'2020-GraphCL] Graph contrastive learning with augmentations. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.neurips.cc/paper_files/paper/2020/file/3fe230348e9a12c13120749e3f9fa4cd-Paper.pdf) - [arXiv'2020-PairwiseDistance/NodeProperty] Self-supervised learning on graphs: Deep insights and new direction. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://arxiv.org/pdf/2006.10141) - [NeurIPS'2020-GROVER] Self-supervised graph transformer on large-scale molecular data. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://proceedings.neurips.cc/paper/2020/file/94aef38441efa3380a3bed3faf1f9d5d-Paper.pdf) - [WWW'2020-GMI] Graph representation learning via graphical mutual information maximization. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3366423.3380112?casa_token=8_d4PlRfYmIAAAAA:uYIQuMXnOVCRWjFlpm3Q2TKpnR-wrMBM_-MRjnS7A_8F8oEqKR5IAK0mXX7bDcP3o9L3_hk_-3MWjn4) - [ICML'2020] When does self-supervision help graph convolutional networks? [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/http://proceedings.mlr.press/v119/you20a/you20a.pdf) - [WWW'2021-GCA] Graph contrastive learning with adaptive augmentation. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/https://dl.acm.org/doi/pdf/10.1145/3442381.3449802?casa_token=J5uSGyBfZzgAAAAA:3ppijn_2zTmgQmUeVpULosGAFxH8EBDZQoupLyb_JMTUBdELSQ27XCKREpudR4rnwn1ZPGEwNkmm2mI) - [ICML'2021-JOAO] Graph contrastive learning automated. [[paper]](https://github.com/Data-Centric-GraphML/awesome-papers/blob/master/http://proceedings.mlr.pr ... ...

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：