{"ID":2824027,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.24246","arxiv_id":"2512.24246","title":"Time-Aware Adaptive Side Information Fusion for Sequential Recommendation","abstract":"Incorporating item-side information, such as category and brand, into sequential recommendation is a well-established and effective approach for improving performance. However, despite significant advancements, current models are generally limited by three key challenges: they often overlook the fine-grained temporal dynamics inherent in timestamps, exhibit vulnerability to noise in user interaction sequences, and rely on computationally expensive fusion architectures. To systematically address these challenges, we propose the Time-Aware Adaptive Side Information Fusion (TASIF) framework. TASIF integrates three synergistic components: (1) a simple, plug-and-play time span partitioning mechanism to capture global temporal patterns; (2) an adaptive frequency filter that leverages a learnable gate to denoise feature sequences adaptively, thereby providing higher-quality inputs for subsequent fusion modules; and (3) an efficient adaptive side information fusion layer, this layer employs a \"guide-not-mix\" architecture, where attributes guide the attention mechanism without being mixed into the content-representing item embeddings, ensuring deep interaction while ensuring computational efficiency. Extensive experiments on four public datasets demonstrate that TASIF significantly outperforms state-of-the-art baselines while maintaining excellent efficiency in training. Our source code is available at https://github.com/jluo00/TASIF.","short_abstract":"Incorporating item-side information, such as category and brand, into sequential recommendation is a well-established and effective approach for improving performance. However, despite significant advancements, current models are generally limited by three key challenges: they often overlook the fine-grained temporal d...","url_abs":"https://arxiv.org/abs/2512.24246","url_pdf":"https://arxiv.org/pdf/2512.24246v1","authors":"[\"Jie Luo\",\"Wenyu Zhang\",\"Xinming Zhang\",\"Yuan Fang\"]","published":"2025-12-30T14:15:06Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[]","has_code":false,"code_links":[{"ID":605545,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2824027,"paper_url":"https://arxiv.org/abs/2512.24246","paper_title":"Time-Aware Adaptive Side Information Fusion for Sequential Recommendation","repo_url":"https://github.com/jluo00/TASIF","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}