SPGL: Enhancing Session-based Recommendation with Single Positive Graph Learning
This work addresses data sparsity and model complexity issues in session-based recommendation for e-commerce and online platforms, presenting an incremental improvement over existing methods.
The paper tackles the problem of data sparsity and high model complexity in session-based recommendation by proposing SPGL, a model that uses single positive optimization loss and graph learning, achieving improved recommendation accuracy as demonstrated on benchmark datasets like Tmall, RetailRocket, and Diginetica.
Session-based recommendation seeks to forecast the next item a user will be interested in, based on their interaction sequences. Due to limited interaction data, session-based recommendation faces the challenge of limited data availability. Traditional methods enhance feature learning by constructing complex models to generate positive and negative samples. This paper proposes a session-based recommendation model using Single Positive optimization loss and Graph Learning (SPGL) to deal with the problem of data sparsity, high model complexity and weak transferability. SPGL utilizes graph convolutional networks to generate global item representations and batch session representations, effectively capturing intrinsic relationships between items. The use of single positive optimization loss improves uniformity of item representations, thereby enhancing recommendation accuracy. In the intent extractor, SPGL considers the hop count of the adjacency matrix when constructing the directed global graph to fully integrate spatial information. It also takes into account the reverse positional information of items when constructing session representations to incorporate temporal information. Comparative experiments across three benchmark datasets, Tmall, RetailRocket and Diginetica, demonstrate the model's effectiveness. The source code can be accessed on https://github.com/liang-tian-tian/SPGL .