Research map / Label-efficient and robust learning / Domain adaptation and generalization
A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| optimize combining coefficients with Algorithm 1 instead of random search | multi-source transfer · CIFAR-10, target n0=100 | accuracy (%): 80.8 -> 83.7 | Helped |
| add source tasks via Algorithm 1 vs using target samples only | multi-source transfer · CIFAR-10, target n0=6 | accuracy (%): 70.9 -> 78.9 | Helped |
| add source tasks via Algorithm 1 vs using target samples only | multi-source transfer · CIFAR-10, target n0=100 | accuracy (%): 81.5 -> 83.7 | Helped |
| random search over combining coefficients vs target-only training | multi-source transfer · CIFAR-10, target n0=6 | accuracy (%): 70.9 -> 67.8 | Hurt |
| multi-source (4 sources) vs best single source | multi-source transfer · CIFAR-10, target n0=100 | accuracy (%): 77.1 -> 83.7 | Helped |
| Algorithm 1 vs UDDA, few-shot | Office-31 · Office-31 six transfer settings | accuracy (%): A->D 89.0 -> 90.0; A->W 88.2 -> 87.3; W->D 97.6 -> 97.2 | Mixed |
| Algorithm 1 vs CPNN (which uses unlabeled data) | Office-Caltech · Office-Caltech six settings | accuracy (%): A->C 78.5 -> 80.3; W->C 73.5 -> 72.9 | Mixed |
Closest papers by meaning
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning (NeurIPS 2025 · similarity 0.90)
- Understanding the Transferability of Representations via Task-Relatedness (NeurIPS 2024 · similarity 0.88)
- Features are fate: a theory of transfer learning in high-dimensional regression (ICML 2025 · similarity 0.87)
- H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer (AAAI 2024 · similarity 0.87)
- Implicit Modeling for Transferability Estimation of Vision Foundation Models (NeurIPS 2025 · similarity 0.87)
- On Transferring Transferability: Towards a Theory for Size Generalization (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.