transferlearning
A curated collection of transfer learning papers, code, datasets and tutorials, mostly in Chinese and English.
- Stars
- 14.4k
- Forks
- 3.8k
- Licence
- MIT
- Language
- Python
- Last update
- 1.7 years ago
- Type
- Curated list
No commits in over a year — check for forks or alternatives before adopting.
What it is
This is a large reference repository about transfer learning, a technique where a model trained on one task or data distribution is reused for another. It collects research papers grouped by topic (domain adaptation, domain generalization, multi-task learning and more), books, video tutorials, datasets, and some runnable code toolboxes such as DeepDA and DeepDG. It is maintained by Jindong Wang and is useful mainly as a map of the field rather than as a single program.
- Find a survey or theory paper on domain adaptation to read first
- Follow the linked PyTorch transfer learning tutorial for fine-tuning a pretrained network
- Explore the DeepDA or DeepDG toolboxes for running domain adaptation or generalization experiments
- Browse listed datasets and benchmarks to compare methods
Great for
- Students starting to learn transfer learning who want reading lists and tutorials
- Researchers looking for papers organized by subtopic such as domain adaptation or domain generalization
- Developers who want reference code for deep domain adaptation experiments
- Chinese-speaking learners, since many resources include Chinese-language material
Not ideal for
- People who want a finished application: this is a collection of resources, not a single tool
- Beginners who need a step-by-step course, since most material links out to external books, videos and slides
- Anyone needing guaranteed up-to-date results: the README's latest paper entries are dated inconsistently and the last push was in February 2025
How to get it
- 1
Clone and build from source
Clone the repository
git clone https://github.com/jindongwang/transferlearning - 2
Run it
- Open the README and read the Introduction and Tutorials section
- Pick a survey or tutorial link to read first
- Open the code folder and choose a toolbox such as DeepDA or DeepDG
- Follow that toolbox's own README to set up its dependencies
- 3
Get the most out of it
- Use the awesome_paper.md file to browse papers by topic
- Check the datasets and benchmarks section before starting an experiment
- Use the linked PyTorch tutorial as a hands-on starting point for fine-tuning
- Try Codespaces or github.dev from the README note to run code without local setup
Downloads
Strengths
- Broad coverage of transfer learning subtopics in one place
- Mixes papers, books, videos and code links, which helps a learner move between levels
- Released under the MIT license, so the linked material and code can be reused under its terms
Trade-offs
- It is a link collection, so quality of each linked item varies and the README is truncated in places
- Some README dates and paper entries look inconsistent, so verify before relying on them
- Much of the material is in Chinese, which may limit use for English-only readers
How it compares
| Project | Stars | Type | Level | Updated | Best for |
|---|---|---|---|---|---|
| transferlearning (this) | 14.4k | Curated list | beginner | 1.7 years ago | Students starting to learn transfer learning who want reading lists and tutorials |
| applied-ml | 30.8k | Curated list | beginner | 2.3 years ago | Engineers planning an ML project who want to see how other companies approached a similar problem |
| awesome-ai-engineering | 22.5k | Curated list | beginner | 15 days ago | Developers who want an overview of the AI engineering topics covered in the description |
| awesome-artificial-intelligence | 16.8k | Curated list | beginner | 3 months ago | Software developers who want to learn the foundations behind language models and agents |
| the-incredible-pytorch | 12.7k | Curated list | beginner | 6 days ago | Beginners looking for PyTorch tutorials and example projects to work through |
| Prompt-Engineering-Guide | 79.8k | Learning resource | beginner | 8 months ago | People who are new to prompting and want structured lessons with examples |
Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.