Get the latest tech news
BeeFormer: CF and CBF hybrid approach for recommendation systems
Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems - recombee/beeformer
Collaborative filtering (CF) methods can capture patterns from interaction data that are not obvious at first sight. Our method is training language models to learn these user behavior patterns from interaction data to transfer that knowledge to previously unseen items. create virtual environment python3.10 -m venv beef and activate it source beef/bin/activate clone this repository and navigate to it cd beeformer install packages pip install -r requirements.txt download the data for movielens: navigate to the_dataset/ml20m folder and run source download_data download the data for goodbooks: navigate to the_dataset/goodbooks folder and run source download_data download the data for amazonbooks: navigate to the_dataset/amazonbooks folder and run source download_data && python preprocess.py in the root folder of the project run the train.py, for example like this:
Or read this on Hacker News