Li Lei

About the model performance of diffnetplus

3

Hi, I run the diffnetplus code on yelp data, get HR=0.3676,NDCG=0.2274, which is consistent with the performance in paper. When I remove the user and item features by`self.fusion_user_embedding = self.user_embedding,...

CUDA ERROR: out of memory

2

when I set the batch_size = 32, after the Epoch 1 training, the validiation will CUDA Error: out of memory. My device is T100, GPU[16G] Aslo, when set batch_size =...

Hi, I set diffnet with different K gcn layers. While for k =0, it means the `self.final_user_embedding = self.fusion_user_embedding + user_embedding_from_consumed_items`, and fixed other components. For yelp, during 300 epochs,...

C-MTEB如何添加自己的数据集进行测试

1

如title

I noticed that you seem to be using data [icliniq-10k](https://drive.google.com/file/d/1ZKbqgYqWc7DJHs3N9TQYQVPdDQmZaClA/view?usp=sharing) from the iCliniq.com website. I am curious to know how you obtained the permission to use their data, as I...