data-scarce settings
Data-scarce settings refer to scenarios where the amount of available training data is limited, posing challenges for model performance and often requiring techniques such as transfer learning or data augmentation to address.
- GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding
- Implicit Generative Property Enhancer
- Learning Crossmodal Interaction Patterns via Attributed Bipartite Graphs for Single-Cell Omics
- Principled Data Augmentation for Learning to Solve Quadratic Programming Problems
- Provably Efficient Multi-Task Meta Bandit Learning via Shared Representations
- VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion