Tag: few-shot learning
Browse our exclusive articles!
Mochi: Efficient Graph Models via Meta-Learning Alignment
Discover Mochi, a meta-learning framework that aligns pre-training and inference for faster, more efficient graph foundation models with superior performan...
1S-DAug: One-Shot Data Augmentation for Few-Shot AI
Discover 1S-DAug, a one-shot data augmentation method boosting few-shot learning accuracy by up to 20% without model retraining.
FSPO: Few-Shot Optimization for Personalized AI Models
Discover FSPO, a novel few-shot optimization method that enhances AI personalization using synthetic preferences for real user adaptation.
Automatic Sample Selection for Improved Few-Shot Learning
Discover how automatic combination of sample selection strategies boosts few-shot learning performance across diverse datasets and models.
MAML-KT: Solving Cold Start in Knowledge Tracing
MAML-KT uses few-shot meta-learning to improve early accuracy in knowledge tracing for new students facing the cold start problem.