用扩散模型净化用户行为序列，动态建模真实兴趣
Adaptive User Interest Modeling via Conditioned Denoising Diffusion For Click-Through Rate Prediction
- 将用户行为视为含噪数据，用条件去噪生成纯净兴趣表示
- 在多个推荐场景下点击率预测效果超越现有方法
- 适合需要精准捕捉动态兴趣的搜索与推荐系统
搜索系统中的用户行为序列如同'兴趣化石'，虽反映真实意图，却受曝光偏差、类别漂移和上下文噪声侵蚀。现有方法多采用'识别-聚合'范式，假设行为序列静态反映偏好，忽视噪声与真实兴趣的交织关系，且输出静态、无上下文感知的表征，无法适应查询-用户-物品-上下文变化下的意图动态演化。为此，我们提出上下文扩散净化器（CDP），将类别过滤后的行为视为'污染观测'，通过前向加噪与条件反向去噪过程，在查询×用户×物品×上下文交叉交互特征引导下，可控生成纯净、上下文感知的兴趣表示，实现随场景动态演化。大量离线与在线实验表明，CDP显著优于当前最优方法。
原文摘要 · Abstract (English)
User behavior sequences in search systems resemble "interest fossils", capturing genuine intent yet eroded by exposure bias, category drift, and contextual noise. Current methods predominantly follow an "identify-aggregate" paradigm, assuming sequences immutably reflect user preferences while overlooking the organic entanglement of noise and genuine interest. Moreover, they output static, context-agnostic representations, failing to adapt to dynamic intent shifts under varying Query-User-Item-Context conditions. To resolve this dual challenge, we propose the Contextual Diffusion Purifier (CDP). By treating category-filtered behaviors as "contaminated observations", CDP employs a forward noising and conditional reverse denoising process guided by cross-interaction features (Query x User x Item x Context), controllably generating pure, context-aware interest representations that dynamically evolve with scenarios. Extensive offline/online experiments demonstrate the superiority of CDP over state-of-the-art methods.
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。