nedjaimanar

in the definition of masked mse function why you set that masked_mse is divided by K.maximum(K.sum(mask_true, axis=-1), 1) and not K.sum(mask_true, axis=-1) ?

when you train a model why you specifie that: validation_data=[users_items_matrix_train_zero, users_items_matrix_validate] and not: [users_items_matrix_train_validate, users_items_matrix_validate]?

when training an autoencoder for rating based collaborative filtering, the weights that are associated to unrated items are not updated, does your custom loss function in DeepRec implementation (masked se)...

in DeepRec implementation, when you've trained the model why you've specified that: validation_data=[users_items_matrix_train_zero, users_items_matrix_validate] and not: [users_items_matrix_train_validate, users_items_matrix_validate]?

does your implementation give the expected result as in the paper?