Models can not distinguish explicit and implicit scenarios.

[PBlithe]

Describe the bug
We refer to the setting rules of explicit data in the API document, but we find that the rating value does not affect the final performance index of the model. We tested NeuMF and EASE models respectively, and the Settings were as follows:

field_separator: "\t"
seq_separator: " "
USER_ID_FIELD: user_id
ITEM_ID_FIELD: item_id
RATING_FIELD: rating
NEG_PREFIX: neg_
LABEL_FIELD: label
load_col:
    inter: [user_id, item_id, rating, timestamp]