search

tengxiao1 / GraphACL

GraphACL: Simple and Asymmetric Graph Contrastive Learning (NeurIPS 2023)
24 stars 2 forks source link

Node Clustering Configuration #2

Open galogm opened 9 months ago

galogm commented 9 months ago

Thanks for sharing the code!

While attempting to reproduce the node clustering results from the appendix, I utilized the node_embeddings generated by the train function in main.py and conducted kmeans on it. However, I'm facing an issue where the NMI results don't match the reported results.

Could you provide details on any specific settings you applied when evaluating node clustering?

Thanks a lot.

lin-uice commented 4 months ago

i read his code,and have some question(may i have poor coding skills) and thought his code is not completely match his paper. bro can you discuss with me?

lin-uice commented 4 months ago

my email is chairuilin@163.com

tengxiao1 commented 4 months ago

We will provide details of node clustering. Different configurations result in different node clustering scores, but the trend for relative improvement should remain the same. @lin-uice Hi, Thanks for your interests. If you have any questions related to the code or the paper, feel free to directly email me (tengxiao01@gmail.com).