用真实评分数据增强推荐系统图模型，提升预测精度。
EDGE-Rec: Efficient and Data-Guided Edge Diffusion For Recommender Systems Graphs
- 提出行-列可分注意力，直接利用评分权重和用户物品特征。
- 基于扩散模型迭代去噪加权交互矩阵，预测结果与原始评分同尺度。
- 适合追求高精度推荐、重视用户物品特征的工业级系统应用。
大多数推荐系统研究聚焦于二值化的历史用户-物品交互编码以预测未来交互，而用户特征、物品特征及交互强度在该领域仍被大量忽视或仅间接使用，尽管这些信息在大规模生产推荐系统中已被证明非常有效。本文提出一种新的注意力机制——行-列可分注意力（Row-Column Separable Attention, RCSA），其思路受协同过滤启发，可直接利用实数值交互权重以及用户和物品特征。在此基础上，进一步提出一种新型图扩散变换器架构（Graph Diffusion Transformer, GDiT），通过迭代去噪方式直接对用户-物品交互图的加权交互矩阵进行建模。该加权交互矩阵由用户-物品双分图结构及其对应的评分交互边权重构建。受文本条件图像生成进展启发，本方法通过一种合理的方式将用户和物品特征作为条件，直接生成与原始评分同量级的用户-物品评分预测结果。
原文摘要 · Abstract (English)
Most recommender systems research focuses on binary historical user-item interaction encodings to predict future interactions. User features, item features, and interaction strengths remain largely under-utilized in this space or only indirectly utilized, despite proving largely effective in large-scale production recommendation systems. We propose a new attention mechanism, loosely based on the principles of collaborative filtering, called Row-Column Separable Attention RCSA to take advantage of real-valued interaction weights as well as user and item features directly. Building on this mechanism, we additionally propose a novel Graph Diffusion Transformer GDiT architecture which is trained to iteratively denoise the weighted interaction matrix of the user-item interaction graph directly. The weighted interaction matrix is built from the bipartite structure of the user-item interaction graph and corresponding edge weights derived from user-item rating interactions. Inspired by the recent progress in text-conditioned image generation, our method directly produces user-item rating predictions on the same scale as the original ratings by conditioning the denoising process on user and item features with a principled approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。