From Mice to Trains: Amortized Bayesian Inference on Graph Data

ArXi:2601.02241v4 Announce Type: replace-cross Graphs arise across diverse domains, from biology and chemistry to social and information networks, as well as in transportation and logistics. Inference on graph-structured data requires methods that are permutation-invariant, scalable across varying sizes and sparsities, and capable of capturing complex long-range dependencies, making posterior estimation on graph parameters particularly challenging.