search

TrustAGI-Lab / MERIT

[IJCAI 2021] A PyTorch implementation of "Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning".
MIT License
39 stars 8 forks source link

Why is the acc different from the MVGRL paper? #3

Closed hcmdgh closed 2 years ago

hcmdgh commented 2 years ago

Hello! In your paper, your acc of MVGRL method on three datasets (Cora, CiteSeer, PubMed) are 82.9, 72.6, 79.4. But in MVGRL paper, the acc are 86.8, 73.3, 80.1. I think both of you use the same dataset, so could you please explain the reason?

KimMeen commented 2 years ago

Hi @hcmdgh, we followed the settings and results in this paper: Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning. You may also refer to this page for more details: https://github.com/kavehhassani/mvgrl/issues/7