Faculty of Computer Science

Univ.-Prof. Dipl.-Ing. Dr. Wilfried Gansterer, M.Sc.

Faculty of Computer Science

Dean

Währinger Straße 29
1090 Wien

wilfried.gansterer(at)univie.ac.at

u:cris portal

Courses

Publications

On Combining Pipelining and s-Step Concepts in Preconditioned Conjugate Gradient Methods. / Mayer, Viktoria ; Gansterer, Wilfried (Corresponding author).
SIAM Conference on Parallel Processing for Scientific Computing (PP26). 2026.

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

doi.org/10.1137/1.9781611979022.6

Numerical Properties and Scalability of s-Step Preconditioned Conjugate Gradient Methods. / Mayer, Viktoria ; Gansterer, Wilfried (Corresponding author).
16th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Heterogeneous Systems (ScalAH25). 2025.

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

doi.org/10.1145/3731599.3767542

Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win. / Kummer, Lorenz; Moustafa, Samir; Ehrlich, Anatol et al.
Proceedings of the 42nd International Conference on Machine Learning. Vol. 267 PMLR, 2025. p. 31991-32010 (Proceedings of Machine Learning Research (PMLR), Vol. 267).

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

Visualization and Analysis of the Loss Landscape in Graph Neural Networks. / Moustafa, Samir (Corresponding author); Kummer, Lorenz; Fetzel, Simon et al.
Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions: 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9–12, 2025, Proceedings, Part V. Springer Cham, 2025. p. 69-81 (Lecture Notes in Computer Science).

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

doi.org/10.1007/978-3-032-04552-2_9

Accelerating Graph Neural Networks Using a Novel Computation-Friendly Matrix Compression Format. / Alves, Joao ; Moustafa, Samir ; Benkner, Siegfried et al.
IEEE International Parallel and Distributed Processing Symposium (IPDPS) 2025. 2025.

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

doi.org/10.1109/IPDPS64566.2025.00100

Adaptive s-step GMRES with randomized and truncated low-synchronization orthogonalization. / Ernstbrunner, Robert ; Gansterer, Wilfried (Corresponding author).
39th IEEE International Parallel Distributed Processing Symposium. 2025.

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

doi.org/10.1109/IPDPS64566.2025.00096

Efficient Mixed Precision Quantization in Graph Neural Networks. / Moustafa, Samir ; Kriege, Nils M.; Gansterer, Wilfried (Corresponding author).
41st IEEE International Conference on Data Engineering. 2025. p. 4038-4052.

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

doi.org/10.1109/ICDE65448.2025.00301

On the Relationship Between Robustness and Expressivity of Graph Neural Networks. / Kummer, Lorenz; Gansterer, Wilfried ; Kriege, Nils Morten.
Proceedings of the 28th International Conference on Artificial Intelligence and Statistics. Vol. 258 PMLR, 2025. p. 1243-1251 (Proceedings of Machine Learning Research (PMLR)).

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks. / Kummer, Lorenz; Moustafa, Samir ; Gansterer, Wilfried et al.
Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence. AAAI, 2025. p. 17990-17998 (Proceedings of the ... National Conference on Artificial Intelligence; No. 17, Vol. 39).

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

doi.org/10.1609/aaai.v39i17.33979

Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Leman Go Indifferent. / Kummer, Lorenz; Moustafa, Samir ; Schrittwieser, Sebastian et al.
Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining: KDD 2024. New York: Association for Computing Machinery (ACM), 2024. p. 1428-1439.

Publications: Contribution to book › Contribution to proceedings › Peer Reviewed

doi.org/10.1145/3637528.3671890

Projects

Algorithmic Data Science for Computational Drug Discovery

Kriege, N. M. (Project Lead) & Gansterer, W. (Co-Lead)

1/05/20 → 30/11/28

Project: Research funding

REPEAL: Resilience versus Performance in Numerical Linear Algebra

Gansterer, W. (Project Lead) & Frolik-Steffan, U. (Admin)

1/03/16 → 31/08/20

Project: Research funding

Verteiltes Rechnen

Gansterer, W. (Project Lead)

6/12/07 → 1/06/14

Project: Research funding