ZhengyanShi comments

Repositories
Issues
Comments

Results 4 comments of


                                            ZhengyanShi

Cannot reproduce the same result posted in the paper. CE loss v.s. BPR loss. Nice try.

# Cannot Reproduce the same results in the paper I have also tried to reproduce the results. I got this by run ``` python run_seq.py --dataset='ml-1m' --train_batch_size=256 lmd=0.1 --lmd_sem=0.1 --model='DuoRec'...

Will you release data and corresponding tags?

Hi, where is the dataset? Thanks

参数问题和精度

您好，感谢您的关注。 > 请问在运行代码前要把use_item_cl_loss和use_sess_cl_loss改为True吗？请参照我提供的sh script来运行代码，比如 `https://github.com/ZhengxiangShi/SelfContrastiveLearningRecSys/tree/main/DHCN`. > 这样的话运算量过大显存容量不够。文章里不是说SCL会降低计算成本吗？可以通过修改 `--sampled_item_size` 的值来调节显存的使用。

参数问题和精度

那可能是你自己的问题