Explore projects

Disentangling the Spectral Properties of the Hodge Laplacian: Not All Small Eigenvalues Are Equal, Vincent P. Grande and Michael T. Schaub, International Conference on Acoustics, Speech, and Signal Processing 2024. https://arxiv.org/abs/2311.14427

"Learning From Simplicial Data Based on Random Walks and 1D Convolutions", Florian Frantzen and Michael T. Schaub, The Twelfth International Conference on Learning Representations, 2024

Accompanying Repository for 'Random Abstract Cell Complexes' Paper.

"Topological Trajectory Classification and Landmark Inference on Simplicial Complexes", Vincent P. Grande, Josef Hoppe, Florian Frantzen, Michael T. Schaub, 2024 Asilomar Conference on Signals, Systems, and Computers, IEEE.

"A Wasserstein Graph Distance Based on Distributions of Probabilistic Node Embeddings", Scholkemper, M., Kühn, D., Nabbefeld, G., Musall, S., Kampa, B., & Schaub, M. T. (2024)

"Efficient Sparsification of Simplicial Complexes via Local Densities of States", Anton Savostianov, Michael T. Schaub, Nicola Guglielmi, Francesco Tudisco, 2025. https://arxiv.org/abs/2502.07558

"HLSAD - Hodge Laplacian-based Simplicial Anomaly Detection", Florian Frantzen, Michael T. Schaub, Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD '25), August 3-7, 2025, Toronto, ON, Canada.

Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs, International Conference on Learning Representations (ICLR 2025), Scholkemper, M.; Wu, X.; Jadbabaie, A. & Schaub, M.

Docker configuration for Jupyter Notebooks using IfcOpenShell for the class "2D3D"

Notebooks for the course "2D3D"

Application language for input and 2D Rendering (Application name sounds to close to MaCoCo, that's why the name is 2DRendering for now)

Parts assembly and 3D models