betsyhj / ksr Goto Github PK

(1)run_KSR.py代码中涉及到的核心数据是
File_ItemEmbedding，File_KBItemEmbedding和File_r_matrix。但是提供的代码似乎没有生成这三个文件的脚本。只是在data目录下有如下脚本：

python deal_movielens.py ml-1m/ratings.dat
python preprocess.py ml-1m/ratings.dattrain_NCF.oneout

请问是否能够提供其他必要的脚本代码。多谢指教了！

Excuse me. We want to use your model for a baseline, but we meet a confusing question that the shown codes have changed for saving user embedding. I'm drowning in codes... Could you provide a version of evalution? Or what is the Y in the method 'model'?
I'm looking forward to your reply. Thanks a million!

Hey bro your code has some intent style and python version unification problems. It'll be helpful if u can fix them as soon as possible. Awsome paper by the way.

As the paper puts it,

For the item side, we further concatenate the item embedding in RS and the entity embedding in KBs, namely q˜i = qi ⊕ ei'.

But it is found to be a theano shared variable which is initialized in the beginning.

self.E = theano.shared(ItemE)

self.KBE = theano.shared(ItemKBE)

self.MergeE = theano.shared(value=np.hstack([ItemE, ItemKBE]), borrow=True)

These 3 embs seems to be indepentdent from each other. Will KBE be updated when MergeE is updated?

Hi, your job on SIGIR-18 is very fascinating and has important realistic significance. However, when I try to reproduce the experiments, I found that there are many uncertainties. For example, in your paper "Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks" , you declared:

we adopt the one-time Freebase [8] dump consisting of 63 million triples

In "KB4Rec: A Dataset for Linking Knowledge Bases with Recommender Systems", you declared:

we use the version of March 2015, which is its latest public version.

But what I found on the homepage of Freebase is:

Which is the actually data set you used for training the KSR algorithm? Or do you use the pre-trained embeddings provided by the thunlp group? Can you provide some further instructions on how to produce the entity embeddings or a method to download the embeddings you used in the experiments? This is an issue of significance to reproduce the experimental results. Any help will be greatly appreciated.

Thanks you very much.

Best regards.