Research map / Label-efficient and robust learning / Recognition and long-tail
Unified Structural Factors for Transfer Learning Generalization with PAC-Bayesian Guarantees
Ziqi Gao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use FOR and ETC together instead of KL, MMD or W2 to predict transfer risk | linear regression predictor · 6 GLUE transfer pairs | R2: 0.11 -> 0.83 | Improved |
| use FOR alone rather than ETC alone (ablation) | linear regression predictor · 6 GLUE transfer pairs | R2: 0.63 -> 0.71 | Improved |
| add ETC to FOR-only predictor (ablation) | linear regression predictor · 6 GLUE transfer pairs | R2: 0.71 -> 0.83 | Improved |
| scale model from BERT-base to BERT-large | fine-tuned BERT · MNLI->RTE | target risk R_T: 0.275 -> 0.241 | Improved |
| scale model from BERT-base to BERT-large | fine-tuned BERT · SST-2->STS-B | target risk R_T: 0.348 -> 0.309 | Improved |
| scale model from BERT-base to BERT-large | fine-tuned BERT · QQP->MRPC | FOR change: +0.01 | No clear effect |
Closest papers by meaning
- 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)
- When is Transfer Learning Possible? (ICML 2024 · similarity 0.86)
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning (NeurIPS 2025 · similarity 0.86)
- Transfer Q-Learning with Composite MDP Structures (ICML 2025 · similarity 0.86)
- On Transferring Transferability: Towards a Theory for Size Generalization (NeurIPS 2025 · similarity 0.85)
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.
