15 citations · 42 across the 10 of their papers we have counts for
4 papers · 1 filter
DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
Pál András Papp, Karolis Martinkus, Lukas Faber +1
This paper studies Dropout Graph Neural Networks (DropGNNs), a new approach that aims to overcome the limitations of standard GNN frameworks. In DropGNNs, we execute multiple runs…
Two-Class (r,k)-Coloring: Coloring with Service Guarantees
Pál András Papp, Roland Schmid, Valentin Stoppiello +1
This paper introduces the Two-Class (,)-Coloring problem: Given a fixed number of colors, such that only of these colors allow conflicts, what is the minimal numb…
Stabilization Bounds for Influence Propagation from a Random Initial State
Pál András Papp, Roger Wattenhofer
We study the stabilization time of two common types of influence propagation. In majority processes, nodes in a graph want to switch to the most frequent state in their neighborhoo…
Debt Swapping for Risk Mitigation in Financial Networks
Pál András Papp, Roger Wattenhofer
We study financial networks where banks are connected by debt contracts. We consider the operation of debt swapping when two creditor banks decide to exchange an incoming payment o…