DIW
Code for the paper "Rethinking Importance Weighting for Deep Learning under Distribution Shift".
Install / Use
/learn @TongtongFANG/DIWREADME
Dynamic Importance Weighting (DIW)
This is a reproducing code for Dynamic Importance Weighting (DIW) in the NeurIPS'20 paper: Rethinking Importance Weighting for Deep Learning under Distribution Shift.
Link to the paper: https://proceedings.neurips.cc//paper/2020/file/8b9e7ab295e87570551db122a04c6f7c-Paper.pdf
Requirements
The code was developed and tested based on the following environment.
- python 3.8
- pytorch 1.6.0
- torchvision 0.7.0
- cudatoolkit 10.2
- cvxopt 1.2.0
- matplotlib
- sklearn
- tqdm
Quick start
You can run an example code of DIW on Fashion-MNIST under 0.4 symmetric label noise.
python diw.py
Example result
After running python diw.py, a output figure and text file of test accurary are made in ./output/ by default.
Citation
If the code is useful in your research, please cite the following:
Tongtong Fang, Nan Lu, Gang Niu, Masashi Sugiyama. Rethinking Importance Weighting for Deep Learning under Distribution Shift. NeurIPS 2020.
Related Skills
YC-Killer
2.7kA library of enterprise-grade AI agents designed to democratize artificial intelligence and provide free, open-source alternatives to overvalued Y Combinator startups. If you are excited about democratizing AI access & AI agents, please star ⭐️ this repository and use the link in the readme to join our open source AI research team.
best-practices-researcher
The most comprehensive Claude Code skills registry | Web Search: https://skills-registry-web.vercel.app
groundhog
398Groundhog's primary purpose is to teach people how Cursor and all these other coding agents work under the hood. If you understand how these coding assistants work from first principles, then you can drive these tools harder (or perhaps make your own!).
isf-agent
a repo for an agent that helps researchers apply for isf funding
