GraphFusionSBR: Denoising Multi-Channel Graphs for Session-Based Recommendation
This work addresses session-based recommendation for users in e-commerce and multimedia, but it is incremental as it builds on existing multi-channel and denoising approaches.
The paper tackled the problem of noisy sessions and item interaction dominance in session-based recommendation systems by proposing a multi-channel model that adaptively removes redundant edges and uses mutual information between channels. Experiments showed enhanced accuracy across e-commerce and multimedia recommendations.
Session-based recommendation systems must capture implicit user intents from sessions. However, existing models suffer from issues such as item interaction dominance and noisy sessions. We propose a multi-channel recommendation model, including a knowledge graph channel, a session hypergraph channel, and a session line graph channel, to capture information from multiple sources. Our model adaptively removes redundant edges in the knowledge graph channel to reduce noise. Knowledge graph representations cooperate with hypergraph representations for prediction to alleviate item dominance. We also generate in-session attention for denoising. Finally, we maximize mutual information between the hypergraph and line graph channels as an auxiliary task. Experiments demonstrate that our method enhances the accuracy of various recommendations, including e-commerce and multimedia recommendations. We release the code on GitHub for reproducibility.\footnote{https://github.com/hohehohe0509/DSR-HK}