# Ricci flow for manifold learning

I know that mean curvature and diffusion-type flows are common in manifold learning because of their smoothing effects. I haven't seen Ricci flow used as much. Given that Ricci and diffusion-type flows behave quite similarly, what is the reason for this (e.g. computational)?

I was thinking that a discrete Ricci flow applied to graphs would have a similar effect to diffusion maps on graphs. I'm not as familiar with Ricci flows, so I don't have an intuition on the geometric behavior of Ricci vs diffusion flows on a graph.