Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
LEAP: Local ECT-Based Learnable Positional Encodings for Graphs
Juan Amboage, Ernst Röell, Patrick Schnider +1
Graph neural networks (GNNs) largely rely on the message-passing paradigm, where nodes iteratively aggregate information from their neighbors. Yet, standard message passing neural…
cs.LG2025
AuToMATo: An Out-Of-The-Box Persistence-Based Clustering Algorithm
Marius Huber, Sara Kalisnik, Patrick Schnider
We present AuToMATo, a novel clustering algorithm based on persistent homology. While AuToMATo is not parameter-free per se, we provide default choices for its parameters that make…