Bridging Optimal Transport, Learning and Structured Data
Modern machine learning increasingly relies on representing complex data through their geometric structure or probability distribution. Geometric Deep Learning has made it possible to encode symmetries, invariances, equivariance, and relational information in non-Euclidean domains, such as graphs and manifolds, with many successful applications, ranging from protein structure prediction to neuroscience.
In parallel, viewing data or features as probability distributions has led to powerful methodologies in deep learning. In particular, optimal transport (OT) provides a natural framework for comparing, aligning, and transforming data distributions, and has contributed to notable advances in generative modeling, attention-based architectures, and representation learning.
This workshop focuses on Geometric Distributional Deep Learning: learning systems that jointly model the geometry and distributional nature of data, features and representations. Our goal is to bring together researchers in geometric deep learning, computational optimal transport, generative modeling, graph and manifold learning, and deep learning theory around a shared question:
How can geometry and distributions be combined to design more scalable, efficient, and interpretable models for structured data?
Adapting optimal transport to graphs, manifolds, and physical systems
Processing probability distributions on graphs and manifolds with GNNs
Sliced methods, entropic regularization, and neural approximations at scale
Diffusion on manifolds, normalizing flows on structured spaces
Molecular modeling, climate prediction, neuroscience, physical sciences
Full-day workshop with invited talks, contributed presentations, and poster sessions
We invite submissions on topics related to geometric distributional deep learning, including but not limited to:
Submissions must follow the NeurIPS 2026 template and instructions. There will be two tracks, one for short papers (2-4 pages) and one for long papiers (5-8 pages). All submissions must be anonymized. Review is double-blind via OpenReview. We welcome ongoing and unpublished works. The workshop is a non-archival venue and will not have official proceedings. Workshop submissions can be subsequently or concurrently submitted to other venues.
All accepted papers will be presented as posters. Selected papers will be invited for contributed talks.