| Posterior network: Uncertainty estimation without ood samples via density-based pseudo-counts B Charpentier, D Zügner, S Günnemann Advances in Neural Information Processing Systems 33, 2020 | 185 | 2020 |
| Graph posterior network: Bayesian predictive uncertainty for node classification M Stadler, B Charpentier, S Geisler, D Zügner, S Günnemann Advances in Neural Information Processing Systems 34, 18033-18048, 2021 | 77 | 2021 |
| Scikit-network: Graph analysis in python T Bonald, N De Lara, Q Lutz, B Charpentier Journal of Machine Learning Research 21 (185), 1-6, 2020 | 70 | 2020 |
| Hierarchical graph clustering using node pair sampling T Bonald, B Charpentier, A Galland, A Hollocou arXiv preprint arXiv:1806.01664, 2018 | 64 | 2018 |
| Natural posterior network: Deep bayesian predictive uncertainty for exponential family distributions B Charpentier, O Borchert, D Zügner, S Geisler, S Günnemann International Conference on Learning Representations, 2021 | 63* | 2021 |
| Evaluating robustness of predictive uncertainty estimation: Are Dirichlet-based models reliable? AK Kopetzki, B Charpentier, D Zügner, S Giri, S Günnemann International Conference on Machine Learning, 5707-5718, 2021 | 49 | 2021 |
| Uncertainty on asynchronous time event prediction M Biloš, B Charpentier, S Günnemann Advances in Neural Information Processing Systems 32, 2019 | 42 | 2019 |
| Edge directionality improves learning on heterophilic graphs E Rossi, B Charpentier, F Di Giovanni, F Frasca, S Günnemann, ... Learning on Graphs Conference, 25: 1-25: 27, 2024 | 35 | 2024 |
| Differentiable DAG Sampling B Charpentier, S Kibler, S Günnemann International Conference on Learning Representations, 2022 | 34 | 2022 |
| Winning the lottery ahead of time: Efficient early network pruning J Rachwan, D Zügner, B Charpentier, S Geisler, M Ayle, S Günnemann International Conference on Machine Learning, 18293-18309, 2022 | 26 | 2022 |
| Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning B Charpentier, R Senanayake, M Kochenderfer, S Günnemann Distribution-Free Uncertainty Quantification Workshop (DFUQ - ICML), 2022 | 25 | 2022 |
| Adversarial training for graph neural networks: Pitfalls, solutions, and new directions L Gosch, S Geisler, D Sturm, B Charpentier, D Zügner, S Günnemann Advances in Neural Information Processing Systems 36, 2024 | 18 | 2024 |
| On out-of-distribution detection with energy-based models S Elflein, B Charpentier, D Zügner, S Günnemann Uncertainty and Robustness in Deep Learning - ICML Workshop, 2021 | 17 | 2021 |
| Accuracy is not the only Metric that matters: Estimating the Energy Consumption of Deep Learning Models J Getzner, B Charpentier, S Günnemann Tackling Climate Change with Machine Learning: Global Perspectives and Local …, 2023 | 10 | 2023 |
| Uncertainty estimation for molecules: Desiderata and methods T Wollschläger, N Gao, B Charpentier, MA Ketata, S Günnemann International conference on machine learning, 37133-37156, 2023 | 8 | 2023 |
| Training, Architecture, and Prior for Deterministic Uncertainty Methods B Charpentier, C Zhang, S Günnemann Pitfalls of limited data and computation for Trustworthy ML Workshop …, 2023 | 6 | 2023 |
| On the Robustness and Anomaly Detection of Sparse Neural Networks M Ayle, B Charpentier, J Rachwan, D Zügner, S Geisler, S Günnemann Sparsity in Neural Networks Workshop (SNN), 2022 | 5 | 2022 |
| Hierarchical graph clustering using node pair sampling. arXiv T Bonald, B Charpentier, A Galland, A Hollocou arXiv preprint arXiv:1806.01664, 2018 | 5 | 2018 |
| Tree sampling divergence: an information-theoretic metric for hierarchical graph clustering B Charpentier, T Bonald IJCAI-19, 2019 | 4 | 2019 |
| Structurally Prune Anything: Any Architecture, Any Framework, Any Time X Wang, J Rachwan, S Günnemann, B Charpentier arXiv preprint arXiv:2403.18955, 2024 | 3 | 2024 |
Stephan GünnemannProfessor of Computer Science, Technical University of MunichVerified email at in.tum.de
