% Key papers for GNN generalization theory (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2020_evolvegcn_102122,
  title = {{EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5984},
}

@inproceedings{aaai2020_measuring_101887,
  title = {{Measuring and Relieving the Over-Smoothing Problem for Graph Neural Networks from the Topological View}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5747},
}

@inproceedings{neurips2021_do_62111,
  title = {{Do Transformers Really Perform Badly for Graph Representation?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27679},
}

@inproceedings{neurips2020_principal_60611,
  title = {{Principal Neighbourhood Aggregation for Graph Nets}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17979},
}

@inproceedings{neurips2020_beyond_59457,
  title = {{Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18186},
}

@inproceedings{neurips2021_representing_63128,
  title = {{Representing Long-Range Context for Graph Neural Networks with Global Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26539},
}

@inproceedings{cvpr2022_robust_19757,
  title = {{Robust Optimization As Data Augmentation for Large-Scale Graphs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{iclr2021_on_30548,
  title = {{On the Bottleneck of Graph Neural Networks and its Practical Implications}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2575},
}

@inproceedings{icml2019_position_37660,
  title = {{Position-aware Graph Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4000},
}

@inproceedings{icml2021_graphnorm_39405,
  title = {{GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10655},
}

@inproceedings{iclr2021_degree_30238,
  title = {{Degree-Quant: Quantization-Aware Training for Graph Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2990},
}

@inproceedings{neurips2021_rethinking_62911,
  title = {{Rethinking Graph Transformers with Spectral Attention}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26970},
}

@inproceedings{neurips2021_large_61678,
  title = {{Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27333},
}

@inproceedings{neurips2019_understanding_59134,
  title = {{Understanding Attention and Generalization in Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13577},
}

@inproceedings{neurips2020_hybrid_60030,
  title = {{Hybrid Models for Learning to Branch}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17077},
}

@inproceedings{neurips2020_rethinking_60714,
  title = {{Rethinking pooling in graph neural networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/19022},
}

@inproceedings{neurips2021_decoupling_62574,
  title = {{Decoupling the Depth and Scope of Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26355},
}

@inproceedings{aaai2021_rethinking_1273,
  title = {{Rethinking Graph Regularization for Graph Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/04573-rethinking-graph-regularization-for-graph-neural-networks/},
}

@inproceedings{icml2020_bayesian_37965,
  title = {{Bayesian Graph Neural Networks with Adaptive Connection Sampling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6755},
}

@inproceedings{cvpr2022_lifelong_19255,
  title = {{Lifelong Graph Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

@inproceedings{cvpr2024_greedyvig_23642,
  title = {{GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30880},
}

@inproceedings{neurips2024_classic_74514,
  title = {{Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97440},
}

@inproceedings{aaai2024_feature_5980,
  title = {{Feature Transportation Improves Graph Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29073},
}

@inproceedings{aaai2024_hongat_6181,
  title = {{HONGAT: Graph Attention Networks in the Presence of High-Order Neighbors}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29615},
}

@inproceedings{aaai2024_learning_6449,
  title = {{Learning Domain-Independent Heuristics for Grounded and Lifted Planning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29986},
}

@inproceedings{aaai2025_graph_9362,
  title = {{Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33404},
}

@inproceedings{neurips2024_relbench_72519,
  title = {{RelBench: A Benchmark for Deep Learning on Relational Databases}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97659},
}

@inproceedings{neurips2024_can_72948,
  title = {{Can Graph Learning Improve Planning in LLM-based Agents?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94464},
}

@inproceedings{neurips2024_on_70344,
  title = {{On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96753},
}

@inproceedings{aaai2025_when_11296,
  title = {{When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33691},
}

@inproceedings{aaai2024_curriculum_5537,
  title = {{Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-Smoothness in Deep GNNs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29256},
}

@inproceedings{aaai2025_naam_10081,
  title = {{NAAM: Node-Aware Attention Mechanism for Distilling GNNs-to-MLP (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35278},
}

@inproceedings{neurips2024_even_71589,
  title = {{Even Sparser Graph Transformers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95681},
}

@inproceedings{aaai2025_generalization_9316,
  title = {{Generalization of Graph Neural Networks Is Robust to Model Mismatch}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35441},
}

@inproceedings{neurips2024_rethinking_71252,
  title = {{Rethinking the Capacity of Graph Neural Networks for Branching Strategy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95991},
}

@inproceedings{neurips2024_graph_73241,
  title = {{Graph Neural Networks Need Cluster-Normalize-Activate Modules}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94196},
}

@inproceedings{iclr2024_a_34720,
  title = {{A Topological Perspective on Demystifying GNN-Based Link Prediction Performance}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18354},
}

@inproceedings{iclr2024_vqgraph_34960,
  title = {{VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18114},
}

@inproceedings{icml2024_two_44570,
  title = {{Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33882},
}

@inproceedings{icml2025_attention_45890,
  title = {{Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46653},
}