Learning Meets Geometry, Graphs, and Networks
We are pleased to announce that registration is open for the 3rd LoG NYC Workshop: Learning Meets Geometry, Graphs, and Networks. This free two-day event serves as a regional branch of the main Learning on Graphs Conference, providing an environment for local researchers to convene, foster discussion, and build social connections. This event includes an invited speaker series, poster session, and reception.
Poster session submissions are open! Submit through the official registration form. For topics in scope, see Subject Areas below.
Details + Dates
- Location: Ingrid Daubechies Auditorium (IDA), Flatiron Institute, 162 5th Ave, New York, NY 10010
- Event Dates: April 21st – 22nd, 2025, 9:00 AM – 6:00 PM ET
- Register By: April 14, 2025, 6:00 PM ET
- Registration Link: Official registration is required for all attendees and is free of charge. Please register here.
- Questions? Please email log-nyc-org@googlegroups.com.
About
The New York Metropolitan Area Regional Workshop of the Learning on Graphs Conference is a semiannual research workshop on topics broadly related to machine learning on graphs and geometry.
Subject Areas
The following is a non-exhaustive summary of our workshop’s research focus. We welcome poster session submissions relevant to these and adjacent topics:
- Expressive graph neural networks
- GNN architectures (e.g., transformers, new positional encodings, etc.)
- Statistical theory on graphs
- Social network analysis
- Causal inference and causal discovery (e.g., structural causal models, causal graphical models, etc.)
- Geometry processing and optimization
- Robustness and adversarial attacks on graphs
- Combinatorial optimization and graph algorithms
- Graph mining
- Graph kernels
- Graph signal processing and spectral methods
- Graph generative models
- Scalable graph learning models and methods
- Graphs for recommender systems
- Temporal graphs
- Knowledge graphs
- Neural manifold
- Self-supervised learning on graphs
- Structured probabilistc inference
- Graph/Geometric ML (e.g., for health applications, security, computer vision, etc.)
- Graph/Geometric ML infrastructures (e.g., datasets, benchmarks, libraries, etc.)