11 papers
Contraction and Hourglass Persistence for Learning on Graphs, Simplices, and Cells
Mattie Ji, Indradyumna Roy, Vikas Garg
Persistent homology (PH) encodes global information, such as cycles, and is thus increasingly integrated into graph neural networks (GNNs). PH methods in GNNs typically traverse an…
The Spacetime of Diffusion Models: An Information Geometry Perspective
RafaÅ Karczewski, Markus Heinonen, Alison Pouplin +2
We present a novel geometric perspective on the latent space of diffusion models. We first show that the standard pullback approach, utilizing the deterministic probability flow OD…
Canonicalizing Multimodal Contrastive Representation Learning
Sharut Gupta, Sanyam Kansal, Stefanie Jegelka +2
As models and data scale, independently trained networks often induce analogous notions of similarity. But, matching similarities is weaker than establishing an explicit correspond…
Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation
Yogesh Verma, Markus Heinonen, Vikas Garg
Protein structure prediction and folding are fundamental to understanding biology, with recent deep learning advances reshaping the field. Diffusion-based generative models have re…
Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models
Najwa Laabid, Severi Rissanen, Markus Heinonen +2
Graph diffusion models, dominant in graph generative modeling, remain underexplored for graph-to-graph translation tasks like chemical reaction prediction. We demonstrate that stan…
Positional Encoding meets Persistent Homology on Graphs
Yogesh Verma, Amauri H. Souza, Vikas Garg
The local inductive bias of message-passing graph neural networks (GNNs) hampers their ability to exploit key structural information (e.g., connectivity and cycles). Positional enc…