SR-GCL: Session-Based Recommendation with Global Context Enhanced Augmentation in Contrastive Learning
This work addresses data sparsity and noise in session-based recommendations for e-commerce, representing an incremental improvement over existing methods.
The paper tackles the problem of session-based recommendation, which predicts user behavior from ongoing sessions, by proposing SR-GCL, a contrastive learning framework with global context enhanced data augmentation, and demonstrates its superiority over state-of-the-art methods on two real-world E-commerce datasets.
Session-based recommendations aim to predict the next behavior of users based on ongoing sessions. The previous works have been modeling the session as a variable-length of a sequence of items and learning the representation of both individual items and the aggregated session. Recent research has applied graph neural networks with an attention mechanism to capture complicated item transitions and dependencies by modeling the sessions into graph-structured data. However, they still face fundamental challenges in terms of data and learning methodology such as sparse supervision signals and noisy interactions in sessions, leading to sub-optimal performance. In this paper, we propose SR-GCL, a novel contrastive learning framework for a session-based recommendation. As a crucial component of contrastive learning, we propose two global context enhanced data augmentation methods while maintaining the semantics of the original session. The extensive experiment results on two real-world E-commerce datasets demonstrate the superiority of SR-GCL as compared to other state-of-the-art methods.