{"ID":2863401,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24424","arxiv_id":"2509.24424","title":"Multi-Item-Query Attention for Stable Sequential Recommendation","abstract":"The inherent instability and noise in user interaction data challenge sequential recommendation systems. Prevailing masked attention models, relying on a single query from the most recent item, are sensitive to this noise, reducing prediction reliability. We propose the Multi-Item-Query attention mechanism (MIQ-Attn) to enhance model stability and accuracy. MIQ-Attn constructs multiple diverse query vectors from user interactions, effectively mitigating noise and improving consistency. It is designed for easy adoption as a drop-in replacement for existing single-query attention. Experiments show MIQ-Attn significantly improves performance on benchmark datasets.","short_abstract":"The inherent instability and noise in user interaction data challenge sequential recommendation systems. Prevailing masked attention models, relying on a single query from the most recent item, are sensitive to this noise, reducing prediction reliability. We propose the Multi-Item-Query attention mechanism (MIQ-Attn) t...","url_abs":"https://arxiv.org/abs/2509.24424","url_pdf":"https://arxiv.org/pdf/2509.24424v1","authors":"[\"Mingshi Xu\",\"Haoren Zhu\",\"Wilfred Siu Hung Ng\"]","published":"2025-09-29T08:11:27Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}