Skip to content

Transfer Learning

Definition
AI-generated

Transfer learning reuses representations or weights trained on a source domain or task (often large-scale pretraining) and adapts them to a target task with fine-tuning, feature extraction, or prompting, improving data efficiency when labels are scarce.

Topics
LLM and Agents
Related
Fine-Tuning Foundation Model Large Language Model (LLM)

Why it matters in GWAS

Biomedical foundation models (genomic sequence, protein, text) are typically transfer-learned to variant scoring, single-cell annotation, or cohort-specific phenotyping. Performance and fairness across ancestries depend on source data diversity; fine-tuning on small biased cohorts can harm portability.

Example usage

"The methods section includes Transfer Learning to support interpretation of the primary findings."

Fine-Tuning Foundation Model Large Language Model (LLM) Machine Learning Neural Network Pretraining Supervised Learning
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Pan SJ, Yang Q. (2010). A survey on transfer learning. IEEE Trans Knowl Data Eng.
← Transcriptomics Transfer RNA (tRNA) →

Last updated (UTC · Git history)