3 papers
cs.LG2026
Graph Neural Networks Are Not Continuous Across Graph Resolutions
Christian Koke, Yuesong Shen, Abhishek Saroha +4
We show that contrary to conventional wisdom in the community, graph neural networks (GNNs) are not continuous with respect to all natural modes of graph convergence. As a result,…
math.FA2026
Di-Graphs with tightly connected Clusters: Effective Graph Laplacians and Resolvent Convergence
Christian Koke
In this note, we study Laplacians on graphs for which connectivity within certain subgraphs tends to infinity. Our main focus are graphs sharing a common node set on which edge wei…
math.FA2026
Large Coupling Convergence Beyond Definiteness
Christian Koke
We study convergence of operator families of the form towards an effective operator defined on , as the coupling constant tends to infinity. Crucially…