5 papers
Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion Models
Nick Dodson, Xinyu Gao, Qingsong Wang +2
Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when memorization versu…
Robust Graph-Based Semi-Supervised Learning via -Conductances
Sawyer Jack Robertson, Chester Holtz, Zhengchao Wan +2
We study the problem of semi-supervised learning on graphs in the regime where data labels are scarce or possibly corrupted. We propose an approach called -conductance learning…
Elucidating Flow Matching ODE Dynamics with Respect to Data Geometries and Denoisers
Zhengchao Wan, Qingsong Wang, Gal Mishne +1
Flow matching (FM) models extend ODE sampler based diffusion models into a general framework, significantly reducing sampling steps through learned vector fields. However, the theo…
Resistance Distance and Linearized Optimal Transport on Graphs
Sawyer Robertson, Zhengchao Wan, Alexander Cloninger
We study the linearization of a discrete transportation distance between probability distributions on finite weighted graphs originally due to Maas (``Gradient flows of the entropy…
Comparing Graph Transformers via Positional Encodings
Mitchell Black, Zhengchao Wan, Gal Mishne +2
The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph.…