[Task] First support of session-based recommendation with RNNs block

[sararb]

Problem:

The integration of session-based support in Merlin Models requires the implementation/refractory of different blocks. (Ticket #433 summarizes the motivation and an overview of all the requirements).

Goal:

• Implement the first low-level support of a session-based model using RNNs.
• This work will include different blocks needed for session-based but won't link them together.

Constraints:

Starting Point:

• First implementation of Masking as an augmentation technique, and the creation of related unit tests.
  [FEA] Design doc for the masking block models#509
  [Task] Target generation for Youtube-DNN retrieval model models#540
  Notes:

• We will include the three approaches: Last, Random, and sliding window (CLM)
• Use the UniformNegativeSampling code as a starting point
• This is a standalone class that transforms the inputs and returns a PredictionOutput object with (inputs, targets, and mask)

• Support of SequenceAggregator operations (to-2d transformation) using ragged tensors: Ignore masking, Average, Weighted-average, Attention-based average. And the creation of related unit tests.
  Notes: We should keep the ragged representation in the input blocks and transform it to a dense representation only when forwarding the sequence to the RNN block.
  Decoupling of InputBlock(v2) and Embedding Tables, support to Ragged Embeddings Lookup and AverageEmbeddingsByWeightFeature models#593

• Support of an RNN block built on top of tf.keras layers: rnn, gru and lstm. And the creation of related unit tests.
  Notes: The block should return either a 2-D representation of the whole sequence or a 3-D representation with all positions. - Dropped as one can directly use tf.keras.layers.LSTM with other MM blocks.

• Example of RNN session-based recommendation training and deployment

  • Session-based example using dressipi dataset and XLNet architecture models#849
  • https://github.com/NVIDIA-Merlin/models/blob/main/examples/usecases/ecommerce-session-based-next-item-prediction-for-fashion.ipynb is an example defining a Bi-LSTM modl