Rethinking the Item Order in Session-based Recommendation with Graph Neural Networks
This work addresses session-based recommendation for e-commerce and media streaming, offering an incremental improvement by integrating graph structures into existing sequential models.
The paper tackles the problem of predicting user preferences in short anonymous sessions for e-commerce and media streaming by modeling item transition patterns beyond simple sequential order. It introduces a graph neural network model that jointly considers sequence and latent graph orders, achieving state-of-the-art performance on Yoochoose and Diginetica datasets.
Predicting a user's preference in a short anonymous interaction session instead of long-term history is a challenging problem in the real-life session-based recommendation, e.g., e-commerce and media stream. Recent research of the session-based recommender system mainly focuses on sequential patterns by utilizing the attention mechanism, which is straightforward for the session's natural sequence sorted by time. However, the user's preference is much more complicated than a solely consecutive time pattern in the transition of item choices. In this paper, therefore, we study the item transition pattern by constructing a session graph and propose a novel model which collaboratively considers the sequence order and the latent order in the session graph for a session-based recommender system. We formulate the next item recommendation within the session as a graph classification problem. Specifically, we propose a weighted attention graph layer and a Readout function to learn embeddings of items and sessions for the next item recommendation. Extensive experiments have been conducted on two benchmark E-commerce datasets, Yoochoose and Diginetica, and the experimental results show that our model outperforms other state-of-the-art methods.