re-run the code you posted and found that it is not as high as reported in the paper, there is some details I missed?

[saladcat]

I re-run code as follow

CUDA_VISIBLE_DEVICES=0 python main.py --dataset=electronic_cell --n_interaction=3 --lambda_s=0.8 --lambda_t=0.8
CUDA_VISIBLE_DEVICES=1 python main.py --dataset=sport_cloth --n_interaction=3 --lambda_s=0.8 --lambda_t=0.8
CUDA_VISIBLE_DEVICES=2 python main.py --dataset=sport_cell --n_interaction=3 --lambda_s=0.8 --lambda_t=0.8
CUDA_VISIBLE_DEVICES=3 python main.py --dataset=electronic_cloth --n_interaction=3 --lambda_s=0.8 --lambda_t=0.8

and dataset generated by run filter_data.py and split_data
but I get thus a result

did I have missed sth?

[sunshinelium]

I am very sorry for the late reply because I am a little busy recently. Maybe you can adjust lambda_s and lambda_t to try it.

[saladcat]

I am very sorry for the late reply because I am a little busy recently. Maybe you can adjust lambda_s and lambda_t to try it.

Thank you for your kindly reply!
would you like to share the value of the two parameter? if you remember them.
and follow the code,I can't generate cell_elec dataset as paper report but other dataset can. so how can I generate cell_elec? there is something wrong with my operation? #4

[sunshinelium]

I'm really sorry for the late reply. In fact, I found later that the pair of datasets of elec_cell filtered users >10 and items >5. it filters in the opposite way to the other data sets.

[miziha-zp]

I'm really sorry for the late reply. In fact, I found later that the pair of datasets of elec_cell filtered users >10 and items >5. it filters in the opposite way to the other data sets.

So would you please provide me with the datasets after your preprocess?