[Task] Improve negative sampling for retrieval

Problem:

There is a considerable amount of tech-debt in the code that’s responsible for negative sampling in retrieval. The biggest issue is that it relies heavily on the model-context, which we would like to remove in order to simplify things.

Goal:

• Simplify the base-class PredictionTask
• Remove the usage of model-context in the prediction-tasks
• Generalize sampling-queues to allow for ranking

Constraints:

• Keep user-facing API the same.

Starting Point:

• Implement PredictionBlock, BinaryPrediction & RegressionPrediction: Done

• Implement a new negative-sampler base class Done

• Implement DotProduct Done

• Implement ContrastivePredictionBlock + tests Done

• Implement DotProductPrediction Done

• Tests for two-tower/mf with BinaryPrediction & RegressionPrediction WIP

• Implement CategoricalPrediction (without contrastive capabilities) Done

• Make CategoricalPrediction allow for negative-sampling Done

• Update retrieval models with new ConstrastiveOutput WIP

• Impelement different types of samplers one by one