heterogeneity
In machine learning contexts, heterogeneity refers to the variability in data sources, model architectures, or environments that can affect performance. Addressing heterogeneity is key to achieving robust and adaptable AI systems.
- Causal Mixture Models: Characterization and Discovery
- Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models
- Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training
- Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs
- REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
- TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction
- Transformers for Mixed-type Event Sequences