S-Walk: Accurate and Scalable Session-based Recommendationwith Random Walks
This addresses accuracy and scalability challenges in session-based recommendation for commercial systems, offering a practical solution with incremental improvements over existing methods.
The paper tackles session-based recommendation by proposing S-Walk, a model that uses random walks with restart to capture intra- and inter-session item relationships, achieving state-of-the-art performance on benchmarks and enabling highly compressed models with inference speeds two or more orders of magnitude faster than DNN-based models.
Session-based recommendation (SR) predicts the next items from a sequence of previous items consumed by an anonymous user. Most existing SR models focus only on modeling intra-session characteristics but pay less attention to inter-session relationships of items, which has the potential to improve accuracy. Another critical aspect of recommender systems is computational efficiency and scalability, considering practical feasibility in commercial applications. To account for both accuracy and scalability, we propose a novel session-based recommendation with a random walk, namely S-Walk. Precisely, S-Walk effectively captures intra- and inter-session correlations by handling high-order relationships among items using random walks with restart (RWR). By adopting linear models with closed-form solutions for transition and teleportation matrices that constitute RWR, S-Walk is highly efficient and scalable. Extensive experiments demonstrate that S-Walk achieves comparable or state-of-the-art performance in various metrics on four benchmark datasets. Moreover, the model learned by S-Walk can be highly compressed without sacrificing accuracy, conducting two or more orders of magnitude faster inference than existing DNN-based models, making it suitable for large-scale commercial systems.