Learning Graphical Models
3acbe9dc3a1e8d48a57b16e9aef91879-Supplemental-Conference.pdf
Machine learning models often fail on out-of-distribution data.
OpenGSL: A Comprehensive Benchmark for Graph Structure Learning
Graph Structure Learning (GSL), a family of data-centric learning approaches, has garnered substantial attention in recent years. The core concept behind GSL is to jointly optimize the graph structure and the corresponding GNN models.
Causal discovery from observational and interventional data across multiple environments
A fundamental problem in many sciences is the learning of causal structure underlying a system, typically through observation and experimentation. Commonly, one even collects data across multiple domains, such as gene sequencing from different labs, or neural recordings from different species.
Flow Matching for Scalable Simulation-Based Inference
Figure 1: Comparison of network architectures (left) and flow trajectories (right). Discrete flows (NPE, top) require a specialized architecture for the density estimator. Continuous flows (FMPE, bottom) are based on a vector field parametrized with an unconstrained architecture.
Flow Matching for Scalable Simulation-Based Inference
Figure 1: Comparison of network architectures (left) and flow trajectories (right). Discrete flows (NPE, top) require a specialized architecture for the density estimator. Continuous flows (FMPE, bottom) are based on a vector field parametrized with an unconstrained architecture.