What is the item_embedding/user_embedding in ncf?

[suhmily]

I wonder how ncf is being used in retrieving and which layer is its item_embedding/user_embedding? I didn't find it in ncf code.

[shenweichen]

NCF has no vectors directly available for vector retrieval. It is a neural network based collaborative filtering method. It still need the original input information to get the matching score of the user and the item through the neural network.

[shuDaoNan9]

NCF has no vectors directly available for vector retrieval. It is a neural network based collaborative filtering method. It still need the original input information to get the matching score of the user and the item through the neural network.

NCF后续会更新加入数值型特征进去吗？ 我看ncf.py签名是yangjieyu，但是@ 不到？

  user_gmf_feature_columns = [SparseFeat(feat, vocabulary_size=size, embedding_dim=user_gmf_embedding_dim)
                                for feat, size in user_feature_columns.items()]
  user_features = build_input_features(user_gmf_feature_columns)

我看这里没单独区分数值型特征。