GitHub - Gasteinh/DSMVC: Deep Safe Multi-view Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase

Gasteinh / DSMVC Public

Notifications You must be signed in to change notification settings
Fork 1
Star 13

Deep Safe Multi-view Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
data		data
models		models
README.txt		README.txt
dataloader.py		dataloader.py
evaluation.py		evaluation.py
kernel.py		kernel.py
loss.py		loss.py
model.py		model.py
requirements.txt		requirements.txt
safe_module.py		safe_module.py
test.py		test.py
train.py		train.py

Repository files navigation

# To start training a new model on provided datasets, e.g., Digit, run:
python train.py --dataset uci

# To test the trained model, e.g., Digit, run:
python test.py --dataset uci

# Due to the divergence based loss may fail into inferior local optima, there may be some fluctuations in the running results, which can be improved by more attempts.

# Acknowledgements
We thank the PyTorch implementation on SiMVC (https://github.com/DanielTrosten/mvc).