3 papers
cs.LG2026
Grothendieck Graph Neural Networks Framework: An Algebraic Platform for Crafting Topology-Aware GNNs
Amirreza Shiralinasab Langari, Leila Yeganeh, Kim Khoa Nguyen
Graph Neural Networks (GNNs) are almost universally built on a single primitive: the neighborhood. Regardless of architectural variations, message passing ultimately aggregates ove…
cs.LG2026
Modeling Topological Impact on Node Attribute Distributions in Attributed Graphs
Amirreza Shiralinasab Langari, Leila Yeganeh, Kim Khoa Nguyen
We investigate how the topology of attributed graphs influences the distribution of node attributes. This work offers a novel perspective by treating topology and attributes as str…
math.CT2025
Representing the language of a topos as quotient of the category of spans
M. Golshani, A. Shiralinasab Langari
We use quotients of span categories to introduce the language of a topos. We also study the logical relations and the quotients of span categories derived from them. As an applicat…