search

cynricfu / MAGNN

Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
388 stars 68 forks source link

Is this normal? #46

Open wangsj12138 opened 1 month ago

wangsj12138 commented 1 month ago

NMI: 0.044030~0.000000 ARI: -0.002919~0.000000

SVM tests summary Macro-F1: 0.225872~0.055853 (0.8), 0.190818~0.025660 (0.6), 0.181179~0.010071 (0.4), 0.172284~0.026592 (0.2) Micro-F1: 0.529167~0.096914 (0.8), 0.508333~0.043899 (0.6), 0.516667~0.029659 (0.4), 0.469792~0.090745 (0.2) K-means tests summary NMI: 0.044030~0.000000 ARI: -0.002919~0.000000 I ran this on a dblp subgraph I got myself. Is this normal? What should normal look like? Maybe there is something wrong? Thanks for your answer.

cynricfu commented 1 month ago

Can other models achieve normal performance on your extracted subgraph? You may also need to check if you properly run the MAGNN preprocessing code on your subgraph.