Dynamic Collaborative Filtering for Matrix- and Tensor-based Recommender Systems
This addresses the need for real-time updates in production recommender systems, though it is incremental as it builds on existing collaborative filtering methods.
The paper tackles the problem of inefficient retraining in recommender systems by introducing TIRecA, a model that updates parameters incrementally with new data, achieving comparable prediction quality to baselines while being 10-20 times faster in training time.
In production applications of recommender systems, a continuous data flow is employed to update models in real-time. Many recommender models often require complete retraining to adapt to new data. In this work, we introduce a novel collaborative filtering model for sequential problems known as Tucker Integrator Recommender - TIRecA. TIRecA efficiently updates its parameters using only the new data segment, allowing incremental addition of new users and items to the recommender system. To demonstrate the effectiveness of the proposed model, we conducted experiments on four publicly available datasets: MovieLens 20M, Amazon Beauty, Amazon Toys and Games, and Steam. Our comparison with general matrix and tensor-based baselines in terms of prediction quality and computational time reveals that TIRecA achieves comparable quality to the baseline methods, while being 10-20 times faster in training time.