Adaptive Long-term Embedding with Denoising and Augmentation for Recommendation
This addresses challenges in personalized recommendation systems for users and platforms, but it is incremental as it builds on existing GNN and sequential modeling techniques.
The paper tackles the problem of noise and static representations in graph-based sequential recommendation systems by introducing ALDA4Rec, which constructs an item-item graph, filters noise, and uses adaptive weighting for long-term embeddings, resulting in outperforming state-of-the-art baselines on four real-world datasets with improvements in accuracy and robustness.
The rapid growth of the internet has made personalized recommendation systems indispensable. Graph-based sequential recommendation systems, powered by Graph Neural Networks (GNNs), effectively capture complex user-item interactions but often face challenges such as noise and static representations. In this paper, we introduce the Adaptive Long-term Embedding with Denoising and Augmentation for Recommendation (ALDA4Rec) method, a novel model that constructs an item-item graph, filters noise through community detection, and enriches user-item interactions. Graph Convolutional Networks (GCNs) are then employed to learn short-term representations, while averaging, GRUs, and attention mechanisms are utilized to model long-term embeddings. An MLP-based adaptive weighting strategy is further incorporated to dynamically optimize long-term user preferences. Experiments conducted on four real-world datasets demonstrate that ALDA4Rec outperforms state-of-the-art baselines, delivering notable improvements in both accuracy and robustness. The source code is available at https://github.com/zahraakhlaghi/ALDA4Rec.