% Key papers for Subgraph and distance-aware GNNs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2019_weisfeiler_101669,
  title = {{Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4384},
}

@inproceedings{iclr2019_how_29203,
  title = {{How Powerful are Graph Neural Networks?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/791},
}

@inproceedings{aaai2021_identity_743,
  title = {{Identity-aware Graph Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/10737-identity-aware-graph-neural-networks/},
}

@inproceedings{neurips2019_graph_58350,
  title = {{Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13698},
}

@inproceedings{neurips2020_distance_59719,
  title = {{Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18045},
}

@inproceedings{aaai2022_kergnns_2284,
  title = {{KerGNNs: Interpretable Graph Neural Networks with Graph Kernels}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/06614-kergnns-interpretable-graph-neural-networks-with-graph-kernels/},
}

@inproceedings{icml2022_how_40656,
  title = {{How Powerful are Spectral Graph Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17795},
}

@inproceedings{neurips2022_how_65945,
  title = {{How Powerful are K-hop Message Passing Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53551},
}

@inproceedings{neurips2021_nested_61435,
  title = {{Nested Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28534},
}

@inproceedings{iclr2022_from_31191,
  title = {{From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6178},
}

@inproceedings{icml2021_breaking_39112,
  title = {{Breaking the Limits of Message Passing Graph Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8577},
}

@inproceedings{iclr2020_what_29254,
  title = {{What graph neural networks cannot learn: depth vs width}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=B1l2bp4YwS},
}

@inproceedings{neurips2019_provably_58852,
  title = {{Provably Powerful Graph Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13416},
}

@inproceedings{iclr2023_graph_33113,
  title = {{Graph Neural Networks for Link Prediction with Subgraph Sketching}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11658},
}

@inproceedings{neurips2021_graph_63555,
  title = {{Graph Neural Networks with Local Graph Parameters}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28409},
}

@inproceedings{aaai2024_union_7702,
  title = {{Union Subgraph Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29551},
}

@inproceedings{icml2021_let_39556,
  title = {{Let’s Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10439},
}

@inproceedings{neurips2022_ordered_66332,
  title = {{Ordered Subgraph Aggregation Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53432},
}

@inproceedings{neurips2023_the_70104,
  title = {{The expressive power of pooling in Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/69873},
}

@inproceedings{aaai2024_weisfeiler_7802,
  title = {{Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29463},
}

@inproceedings{neurips2024_spatio_71076,
  title = {{Spatio-Spectral Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96137},
}

@inproceedings{neurips2024_exploring_73102,
  title = {{Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94327},
}

@inproceedings{icml2024_position_45695,
  title = {{Position: Future Directions in the Theory of Graph Machine Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32757},
}

@inproceedings{icml2025_expressive_48740,
  title = {{Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43882},
}

@inproceedings{icml2025_covered_49065,
  title = {{Covered Forest: Fine-grained generalization analysis of graph neural networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43559},
}

@inproceedings{neurips2025_spectral_75036,
  title = {{Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=3dnG7LcKxT},
}

@inproceedings{iclr2026_the_84975,
  title = {{The Logical Expressiveness of Topological Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=8w8jzJXjhj},
}

@inproceedings{neurips2026_how_92085,
  title = {{How Hard Is It for Message-Passing GNNs to Simulate One Weisfeiler-Lehman Color-Refinement Step?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/151609},
}

@inproceedings{neurips2026_gnns_94398,
  title = {{GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/151409},
}

@inproceedings{aaai2026_spectral_106737,
  title = {{Spectral Basis Learning for Expressive Graph Neural Networks in Link Prediction}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39044},
}

@inproceedings{aaai2026_lgan_106880,
  title = {{LGAN: An Efficient High-Order Graph Neural Network via the Line Graph Aggregation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39232},
}

@inproceedings{icml2026_invgnn_54415,
  title = {{InvGNN: Learning Invertible Node Representations on Graphs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=okKDijCwRn},
}

@inproceedings{iclr2025_on_81607,
  title = {{On Designing General and Expressive Quantum Graph Neural Networks with Applications to MILP Instance Representation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30170},
}

@inproceedings{iclr2025_higher_82210,
  title = {{Higher-Order Graphon Neural Networks: Approximation and Cut Distance}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29581},
}

@inproceedings{neurips2026_beamwitness_95041,
  title = {{BeamWitness: Rooted Subgraph Beam Search for Selective Graph Representation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/149610},
}