Dinxin

Can you release the code of the associated baseline approaches such as NeuMF?

7

I can feed the gowalla dataset into the NeuMF model implemented by the repo in the url "https://github.com/hexiangnan/neural_collaborative_filtering". Surprisingly, the NDCG@10 can achieve 0.3991... But you reported the NDCG@20 is...

Why does GPU usage so low?

1


Can you supply the instructions about how to use real-world data to train model

18

I viewed the whole code and found that the code only use toy dummy data to train model. So I don't really understand how you use those data to train...

Question about more datasets and more baselines

2

Why don't you give the associated experimental results on some regression tasks in the MoleculeNet benchmark? Additionally, there are some pertaining techniques tailored for molecule data such as mol2vec, seq2seq...

I downloaded the steam dataset displayed on https://cseweb.ucsd.edu/~jmcauley/datasets.html, and I found that purchase and play behaviors are in the same file named "australian_users_items.json" while review and recommend data are in...

Difference of readout function in code vs. paper

1

We noticed that the readout function in the original paper is concatenation, while the one in code implementation is addition.

Order of Inter-Message Passing?

1

What are the order of the coarse-to-fine information flow and the fine-to-coarse information flow? Which information flow is put ahead of another ?