Search Results for author:
Found 4 papers, 0 papers with code
Learn To Learn More Precisely
Then in the outer loop, MSD utilizes the same query data to optimize the consistency of learned knowledge, enhancing the model's ability to learn more precisely.
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
Based on our findings, we propose Task Groupings Regularization, a novel approach that benefits from model heterogeneity by grouping and aligning conflicting tasks.
FREE: Faster and Better Data-Free Meta-Learning
Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts constrained by data privacy concerns.
Task-Distributionally Robust Data-Free Meta-Learning
TDS leads to a biased meta-learner because of the skewed task distribution towards newly generated tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
