{"ID":2891728,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16396","arxiv_id":"2507.16396","title":"Knowledge-aware Diffusion-Enhanced Multimedia Recommendation","abstract":"Multimedia recommendations aim to use rich multimedia content to enhance historical user-item interaction information, which can not only indicate the content relatedness among items but also reveal finer-grained preferences of users. In this paper, we propose a Knowledge-aware Diffusion-Enhanced architecture using contrastive learning paradigms (KDiffE) for multimedia recommendations. Specifically, we first utilize original user-item graphs to build an attention-aware matrix into graph neural networks, which can learn the importance between users and items for main view construction. The attention-aware matrix is constructed by adopting a random walk with a restart strategy, which can preserve the importance between users and items to generate aggregation of attention-aware node features. Then, we propose a guided diffusion model to generate strongly task-relevant knowledge graphs with less noise for constructing a knowledge-aware contrastive view, which utilizes user embeddings with an edge connected to an item to guide the generation of strongly task-relevant knowledge graphs for enhancing the item's semantic information. We perform comprehensive experiments on three multimedia datasets that reveal the effectiveness of our KDiffE and its components on various state-of-the-art methods. Our source codes are available https://github.com/1453216158/KDiffE.","short_abstract":"Multimedia recommendations aim to use rich multimedia content to enhance historical user-item interaction information, which can not only indicate the content relatedness among items but also reveal finer-grained preferences of users. In this paper, we propose a Knowledge-aware Diffusion-Enhanced architecture using con...","url_abs":"https://arxiv.org/abs/2507.16396","url_pdf":"https://arxiv.org/pdf/2507.16396v1","authors":"[\"Xian Mo\",\"Fei Liu\",\"Rui Tang\",\"Jintao\",\"Gao\",\"Hao Liu\"]","published":"2025-07-22T09:47:56Z","proceeding":"cs.MM","tasks":"[\"cs.MM\",\"cs.IR\"]","methods":"[\"Graph Neural Network\",\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":611914,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2891728,"paper_url":"https://arxiv.org/abs/2507.16396","paper_title":"Knowledge-aware Diffusion-Enhanced Multimedia Recommendation","repo_url":"https://github.com/1453216158/KDiffE","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}