AI RESEARCH
From Layers to Networks: Comparing Neural Representations via Diffusion Geometry
arXiv CS.LG
•
ArXi:2605.15901v1 Announce Type: new Diffusion geometry is a manifold learning framework that uses random walks defined by Marko transition matrices to characterize the geometry of a dataset at multiple scales. We use diffusion geometry for neural representations, incorporating tools from multi-view learning into this field for the first time.