8 problems

The experiments compare graphcodes with one-parameter methods on orbit datasets. The graphcode-GNN pipeline is evaluated against several one-parameter persistence methods as the da…

Graph Transformers (GTs) use propagation graphs whose edge geometry is described by the Continuous Unified Ricci Curvature (CURC), and the initial propagation graphs are complete g…

Let $G=(V,E,w)$ be a graph with features given by a map $f:V\to M$ into a Riemannian manifold, and suppose the graph's features have a convex bounding ball. Convergence conjecture.…

For an integer $k\ge 2$, let Local $k$-FGNN, Local $k$-GNN, and $k$-FGNN denote the corresponding higher-order graph neural network architectures, ordered by their ability to disti…

Let a GNN architecture be defined by a general form of color-refinement procedure that outputs stable color mappings, and let its homomorphism expressivity mean the graph-pattern i…

Consider the graph unconstrained feature model (gUFM) in the objective defined by equation ( … (s{c1,1},ldots,s{cC,1})=cdots=(s{c1,n},ldots,s{cC,n}),qquad forall cin[C]. … ), if an…

Polynomial-functor conjecture. This integral transform can be described as a polynomial functor, with $p_\otimes$ and $o_\oplus$ corresponding respectively to the dependent product…

Graph Neural Networks (GNNs) are machine-learning models applied to the traffic network, in which relationships and interdependencies between arcs and their counts are modeled expl…