skip to content

Center for Data and Simulation Science

Aleksandar Bojchevski leads the Trustworthy Artificial Intelligence Lab (TAIL) whose research is about models and algorithms that are not only accurate or efficient, but also robust, uncertainty-aware, privacy-preserving, fair, and interpretable. These trustworthiness aspects are essential in high-stakes applications and decision-making contexts that involve humans. The lab aims to develop methods that can reliably handle the long tail of real world data which may be noisy, adversarial, or anomalous, and subject to distribution shifts. One research thread focuses on imbuing models with guarantees in the form of robustness certificates and distribution-free prediction sets. Another thread is dedicated to developing trustworthy graph-based models like graph neural networks.

Selected publications

  1. S. H. Zargarbashi, S. Antonelli, and A. Bojchevski, "Conformal Prediction Sets for Graph Neural Networks", In International Conference on Machine Learning (ICML), 2023.
  2. S. M. Akhondzadeh, V. Lingam, and A. Bojchevski, "Probing Graph Representations", In International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.
  3. F. Mujkanovic, S. Geisler, S. Günnemann, and A. Bojchevski, "Are Defenses for Graph Neural Networks Robust?" In Conference on Neural Information Processing Systems (NeurIPS), 2022.
  4. Y. Scholten, J. Schuchardt, S. Geisler, A. Bojchevski, and S. Günnemann, "Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks", In Neural Information Processing Systems (NeurIPS), 2022.
  5. J. Schuchardt, A. Bojchevski, J. Klicpera, and S. Günnemann, "Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks", In International Conference on Learning Representations (ICLR), 2021.
  6. A. Bojchevski, J. Gasteiger, and S. Günnemann, "Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More", In International Conference on Machine Learning (ICML), 2020.
  7. A. Bojchevski, J. Gasteiger, B. Perozzi, A. Kapoor, M. Blais, B. Rózemberczki, M. Lukasik, and S. Günnemann, "Scaling Graph Neural Networks with Approximate PageRank", In International Conference on Knowledge Discovery and Data Mining (KDD), 2020.
  8. A. Bojchevski, and S. Günnemann, "Certifiable Robustness to Graph Perturbations”, In Neural Information Processing Systems (NeurIPS), 2019.
  9. J. Klicpera, A. Bojchevski, and S. Günnemann, "Predict then Propagate: Graph Neural Networks meet Personalized PageRank", In International Conference on Learning Representations (ICLR), 2019.
  10. A. Bojchevski, and S. Günnemann, "Adversarial Attacks on Node Embeddings via Graph Poisoning", In International Conference on Machine Learning (ICML), 2019.