3 papers
cs.LG2026
VillageNet: Graph-based, Easily-interpretable, Unsupervised Clustering for Broad Biomedical Applications
Aditya Ballal, Gregory A. DePaul, Esha Datta +5
Clustering large high-dimensional datasets with diverse variable is essential for extracting high-level latent information from these datasets. Here, we developed an unsupervised c…
cs.SI2025
Tight Practical Bounds for Subgraph Densities in Ego-centric Networks
Connor Mattes, Esha Datta, Ali Pinar
Subgraph densities play a crucial role in network analysis, especially for the identification and interpretation of meaningful substructures in complex graphs. Localized subgraph d…
cs.LG2025
Topology of Out-of-Distribution Examples in Deep Neural Networks
Esha Datta, Johanna Hennig, Eva Domschot +2
As deep neural networks (DNNs) become increasingly common, concerns about their robustness do as well. A longstanding problem for deployed DNNs is their behavior in the face of unf…