Accelerating Generative Recommendation via Simple Categorical User Sequence Compression
By: Qijiong Liu , Lu Fan , Zhongzhou Liu and more
Potential Business Impact:
Makes online shopping suggestions faster and more accurate.
Although generative recommenders demonstrate improved performance with longer sequences, their real-time deployment is hindered by substantial computational costs. To address this challenge, we propose a simple yet effective method for compressing long-term user histories by leveraging inherent item categorical features, thereby preserving user interests while enhancing efficiency. Experiments on two large-scale datasets demonstrate that, compared to the influential HSTU model, our approach achieves up to a 6x reduction in computational cost and up to 39% higher accuracy at comparable cost (i.e., similar sequence length).
Similar Papers
Efficient Sequential Recommendation for Long Term User Interest Via Personalization
Information Retrieval
Makes movie suggestions faster and better.
Generative Chain of Behavior for User Trajectory Prediction
Information Retrieval
Predicts what you'll want to see next.
Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders
Information Retrieval
Makes online suggestions faster with long histories.