SSOTTY

会话中的物品顺序

4

由于会话划分时只使用会话ID进行排序，一个会话内物品的顺序是不是乱序的？ data = data.sort_values(by=['TimeId']).groupby('SessionId')['ItemId'].apply(list).to_dict()

SocialRec中的samples

1

在SocialRec中，samples1和samples2的默认值分别为10和5。如果我没理解错的话samples1代表第二层邻居的数量，samples2代表第一层邻居的数量，这样的话第二层邻居的数量就比第一层邻居的数量还多，与经验不符。而且您的论文中也写到“The neighborhood sample sizes are empirically set to 10 and 15 in the first and second convolutional layers”，请问是少写了一个1吗？

more question about dataset

1

When n = 10，I find more than 10% were removed out of a total of 817,741 adoptions and more than 10K item is remained， which is inconsistent with the data...