yueliu1999 / DCRN

[AAAI 2022] An official source code for paper Deep Graph Clustering via Dual Correlation Reduction.
MIT License
219 stars 31 forks source link

How about the time complexity of DCRN, I have run it with GPU and I found It's speed is slowly #5

Open yuxiaokang-source opened 2 years ago

yueliu1999 commented 2 years ago

I also find this problem in my experiments. However, the training process would not bring lots of time costs since they are all performed on the GPU. However, I observe that the K-means algorithm in scikit-learn package is running on the CPU, leading to higher time costs. Maybe you can move the K-means algorithm to the GPU to speed up DCRN. Some implements of K-means on GPU can be found in the following links.

https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering/blob/main/dgc/clustering/kmeans_gpu.py

https://github.com/subhadarship/kmeans_pytorch

https://github.com/NVIDIA/kmeans