Guorui Zhou et al. “Deep Interest Network for Click-Through Rate Prediction” in ACM SIGKDD 2018
- Reference code:
Deep Interest Network utilizes the attention mechanism to get the weight of each user’s behavior according to the target items, and finally gets the user representation.
In the official source code, unlike the paper, user features and context features are not input into DNN. We just migrated and changed the official source code. But You can get user features embedding from user_feat_list. Besides, in order to compare with other models, we use AUC instead of GAUC to evaluate the model.
Calculate the training loss for a batch data.
interaction (Interaction) – Interaction class of the batch.
Training loss, shape: 
- Return type
forward(user, item_seq, item_seq_len, next_items)¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Although the recipe for forward pass needs to be defined within this function, one should call the
Moduleinstance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.