search

rusty1s / pytorch_cluster

PyTorch Extension Library of Optimized Graph Cluster Algorithms
MIT License
816 stars 146 forks source link

classical K-Means clustering #31

Closed qiulesun closed 3 years ago

qiulesun commented 5 years ago

The classical K-Means clustering has been also widely used in many papers, including graph-based repreentation learning. Could you consider implementing it as a new feature?

rusty1s commented 5 years ago

Could you give me some pointers where k-means is used in combination with deep graph representation learning? Couldn't you simply use something like scikit-learn for this?

qiulesun commented 5 years ago

@rusty1s Does the script nearest.py directly implement the K-means clustering described in Section 3.3 (Initialization by Clustering) of NeurIPS2018 paper https://www.biostat.wisc.edu/~yli/preprints/yin_nips2018_camera_ready.pdf ?

rusty1s commented 5 years ago

The nearest method implements the batch-wise cluster assignment in the k-means algorithm. You need to then iteratively refine the cluster centers based on those assignments.

github-actions[bot] commented 3 years ago

This issue had no activity for 6 months. It will be closed in 2 weeks unless there is some new activity. Is this issue already resolved?