Optimal transport implementation for domain adaptaion for cross domain reccomendation
  • Jupyter Notebook 50.9%
  • Python 48.9%
  • Shell 0.2%
Find a file
2025-09-22 00:58:12 +09:00
.vscode experimental framework from claude 2025-09-17 14:56:00 +09:00
DArec_opt update comprehensive 2025-09-22 00:58:12 +09:00
data silly notebooks 2025-09-17 14:54:07 +09:00
examples experimental framework from claude 2025-09-17 14:56:00 +09:00
experiment_framework experimental framework from claude 2025-09-17 14:56:00 +09:00
I-DArec fix dumb import 2025-09-16 22:53:45 +09:00
reference add graph optimal transport reference code 2025-09-16 14:06:45 +09:00
U-DArec fix dataloading so training actually works 2025-09-16 22:13:50 +09:00
.gitignore ignore image outputs 2025-09-18 01:06:01 +09:00
.gitmodules add graph optimal transport reference code 2025-09-16 14:06:45 +09:00
.python-version add uv versioning 2025-09-16 15:08:01 +09:00
pyproject.toml for debugging 2025-09-21 21:16:04 +09:00
README.md add data preprocessing instructions 2025-09-16 20:17:40 +09:00
run_experiments.py experimental framework from claude 2025-09-17 14:56:00 +09:00
uv.lock bump uv.lock 2025-09-21 21:16:10 +09:00
visualize_embeddings.ipynb silly notebooks 2025-09-17 14:54:07 +09:00

Running this yourself

uv sync

you want to start by downloading the data. No Guarentees that the links still work:

./data/download.sh

Then you want to run the preprocessing to generate the correct numpy matricies. You can run the original DARec code if you would like using the corresponding Data_Preprocessing.py or you can trust I implemented the multi-mode version and it all works with:

python DArec_opt/Data_Preprocessing.py