Graphs serve as a powerful representational framework for machine learning, and their integration has substantially advanced the field. Indeed, extensive studies have pushed forward graph machine learning (GML) in both theory and applications. Recently, new perspectives have been emerging in the machine learning community, including algebraic–topological analyses, foundation models, generative models, and large models in applications. Leveraging these ideas for core graph machine learning holds a lot of promise, including the dual benefit of deeper theoretical insight, new capabilities and more powerful, application-aligned algorithms and models. The aim of this workshop is to explore and connect these new perspectives on GML, and to identify overarching challenges and tools – in terms of theory, methodology, and modeling.
Call for papers
This workshop will receive submissions, talks, and poster sessions on a wide range of topics, perspectives, and ideas including but not limited to:
- Symmetry, Equivariance, and Group-Theoretic Graph Models
- Continuous and Differential Geometric Models
- Topological Machine Learning
- Graph Diffusion Models and Graph Generative Models
- Graph foundational models and Graph Augmented LLMs
- Continuous‑Limit and Infinite‑Width Analysis of Graph Machine Learning
- Transferability and Generalization Properties of Graph Models
- Graphs for Science and Graph-Based Simulations
- Novel Graph Machine Learning Architectures
- Causality and Directed Acyclic Graph learning
- Self-supervised and Semi-supervised Graph Machine Learning
- Quantum Graph Machine Learning
The main text of a submitted paper is limited to 6 content pages, including all figures and tables. We encourage submissions to have between 4 and 6 pages. Additional pages containing references, checklist, and the optional technical appendices do not count as content pages. All submission are double blind, and must use the NeurIPS 2025 author kit available here. The review process will be facilitated via OpenReview. Please make sure every author has an OpenReview account ahead of submission.
As per the NeurIPS workshop guidelines, this workshop is not a venue for work that has been previously published in other conferences on machine learning or related fields.
Accepted papers will be accessible via this website ahead of the workshop. Our workshop is non-archival and there are no formal proceedings.
The submission portal can be found here.
Dates and Deadlines
| Date | |
|---|---|
| September 2nd, 2025, 11:59 pm AoE | Submission deadline |
| September 22nd, 2025, 11:59 pm AoE | Accept/Reject Notification Date |
| December 6 or December 7, 2025 | Workshop Date |
Program
| Time | Session |
|---|---|
| 08:45–09:00 | Opening Remarks: Goals, code of conduct, logistics |
| 09:00–09:45 | Keynote 1 |
| 09:45–10:15 | Contributed Talks: 10 min talk + Q&A |
| 10:15–10:45 | Coffee and Posters A |
| 10:45–11:30 | Keynote 2 |
| 12:00–13:30 | Lunch |
| 13:30–14:15 | Keynote 3 |
| 14:15–15:00 | Contributed Talks |
| 15:00–15:30 | Coffee and Posters B |
| 15:30–16:15 | Keynote 4 |
| 16:15–16:45 | Panel Discussion: “What’s next for GML?” |
| 16:15–17:00 | Keynote 5 |
| 17:00–17:45 | Mentorship Speed‑Networking |
| 17:45–18:00 | Closing Remarks: Awards, next steps, resources |
Speakers
Jure Leskovec
Professor of Computer Science at Stanford University.
Yusu Wang
Professor in Halιcιoğlu Data Science Institute at University of California, San Diego.
Nina Miolane
Assistant Professor of Electrical and Computer Engineering at UC Santa Barbara.
Bryan Perozzi
Research Scientist at Google Research.
Mathias Niepert
Professor (W3) at the University of Stuttgart and a faculty member of the International Max Planck Research School for Intelligent Systems.
Panelists
Soledad Villar
Assistant Professor at the Department of Applied Mathematics & Statistics, and Mathematical Institute for Data Science at Johns Hopkins University.
Nayat Sanchez-Pi
Executive Director - CEO Inria Chile Foundation.
Organizers
Juan Cervino
Postdoctoral Researcher at Massachusetts Institute of Technology.
Stefanie Jegelka
Associate Professor (on leave) at MIT EECS, and a Humboldt Professor at TU Munich.
Charilaos Kanatsoulis
Research Associate in the Department of Computer Science at Stanford University.
Alejandro Ribeiro
Professor of Electrical and Systems Engineering at the University of Pennsylvania.
Luana Ruiz
Assistant Professor, Department of Applied Mathematics and Statistics, Johns Hopkins University
Zhiyang Wang
Postdoc Scholar in Halıcıoğlu Data Science Institute at UCSD.
Area Chairs
| Name | Institution |
|---|---|
| Michael A. Perlmutter | Assistant Professor at Boise State University |
| Venkata S.S. Gandikota | Assistant Professor at Syracuse University |
| Gonzalo Mateos | Professor at University of Rochester |
| Ellen Vitercik | Assistant Professor at Stanford University |
| Kaixiong Zhou | Assistant Professor at North Carolina State University |
| Jundong Li | Assistant Professor at University of Virginia |
| Michael Galkin | Senior Research Scientist at Google Research |
| Jhony Giraldo | Assistant Professor at Institut Polytechnique de Paris |
| Alex Tong | Assistant Professor at Duke University |
| Yuning You | Postdoc at California Institute of Technology |
| Siheng Chen | Associate Professor at Shanghai Jiao Tong University |
| Melanie Weber | Assistant Professor at Harvard University |
Contact
Do not hesitate to write us for any questions:
graphneurips2025@googlegroups.com
This website was built with Hugo and the Hugo Scroll template.