Residual feature integration with a trainable target-side encoder provably prevents negative transfer, achieving convergence rates no worse than training from scratch under informative target distributions.
Deep transfer learning: Model framework and error analysis
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A two-step spectral embedding procedure that removes irrelevant components from a knowledge matrix then projects to recover shared and heterogeneous signals for rare-disease clinical concept and patient embeddings.
citing papers explorer
-
Residual Feature Integration is Sufficient to Prevent Negative Transfer
Residual feature integration with a trainable target-side encoder provably prevents negative transfer, achieving convergence rates no worse than training from scratch under informative target distributions.
-
Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records
A two-step spectral embedding procedure that removes irrelevant components from a knowledge matrix then projects to recover shared and heterogeneous signals for rare-disease clinical concept and patient embeddings.