UniRec is an easy-to-use, lightweight, and scalable implementation of recommender systems. Its primary objective is to enable users to swiftly construct a comprehensive ecosystem of recommenders using a minimal set of robust and practical recommendation models.
This PR introduces a new data format to specify maximum sequence lengths for user interactions and updates the processing of sequential datasets by dropping the first interaction.
Checklist:
[x] Added "user-item-max_len" data format
[x] Dropped the first interaction in sequential datasets
[x] Included split-run_prepare_data-ml-100k-sequential-max_len.sh and train_seq_model_ml100k_max_len.sh for data preparation and model training validation
This PR introduces a new data format to specify maximum sequence lengths for user interactions and updates the processing of sequential datasets by dropping the first interaction.
Checklist:
split-run_prepare_data-ml-100k-sequential-max_len.sh
andtrain_seq_model_ml100k_max_len.sh
for data preparation and model training validation