Graph neural networks for maximum constraint satisfaction J Toenshoff, M Ritzert, H Wolf, M Grohe Frontiers in artificial intelligence 3, 580607, 2021 | 57* | 2021 |
Walking out of the weisfeiler leman hierarchy: Graph learning beyond message passing J Tönshoff, M Ritzert, H Wolf, M Grohe arXiv preprint arXiv:2102.08786, 2021 | 41* | 2021 |
Wl meet vc C Morris, F Geerts, J Tönshoff, M Grohe International Conference on Machine Learning, 25275-25302, 2023 | 16 | 2023 |
Learning the language of QCD jets with transformers T Finke, M Krämer, A Mück, J Tönshoff Journal of High Energy Physics 2023 (6), 1-18, 2023 | 13 | 2023 |
Where did the gap go? reassessing the long-range graph benchmark J Tönshoff, M Ritzert, E Rosenbluth, M Grohe arXiv preprint arXiv:2309.00367, 2023 | 10 | 2023 |
Some might say all you need is sum E Rosenbluth, J Toenshoff, M Grohe arXiv preprint arXiv:2302.11603, 2023 | 9 | 2023 |
One model, any csp: Graph neural networks as fast global search heuristics for constraint satisfaction J Tönshoff, B Kisin, J Lindner, M Grohe arXiv preprint arXiv:2208.10227, 2022 | 9 | 2022 |
Stable Tuple Embeddings for Dynamic Databases J Toenshoff, N Friedman, M Grohe, B Kimelfeld 2023 IEEE 39th International Conference on Data Engineering (ICDE), 1286-1299, 2023 | 2* | 2023 |
Selecting Walk Schemes for Database Embedding Y Lev Lubarsky, J Tönshoff, M Grohe, B Kimelfeld arXiv e-prints, arXiv: 2401.11215, 2024 | | 2024 |
Transformers vs. Message Passing GNNs: Distinguished in Uniform J Tönshoff, E Rosenbluth, M Ritzert, B Kisin, M Grohe The Twelfth International Conference on Learning Representations, 2023 | | 2023 |