适配知识图谱用于序列推荐中的行为去噪
Adapting Knowledge Graphs for Behavior Denoising in Sequential Recommendation
- Northeastern University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出AdaptedKG，通过为每个训练样本推导校准后的知识图谱证据，实现序列推荐中的行为去噪，在标准及多个行为去噪序列推荐器上均取得性能提升。
AI中文摘要：
序列推荐根据用户的交互历史预测下一个项目，但并非所有交互都具有同等信息价值。实际日志中包含持久偏好、临时需求、探索行为和偶然行为，部分交互会扭曲历史表示或提供不可靠的监督。现有的去噪方法主要从共现、顺序或模型预测的角度判断此类交互，未利用项目间关系的明确证据。知识图谱（KG）可提供此类证据，但项目流行度、图度、覆盖不均及广泛共享的实体会放大连通性并使可靠性估计产生偏差。本文提出AdaptedKG，该方法为每个训练样本推导校准后的KG证据，无需将图表示添加到推荐模型中。它首先将观测上下文与结构匹配的替代项进行比较，识别异常突出的关系路径以构建局部KG视图；随后将每个交互与结构匹配的参考项目进行比较，在该视图内校准其支持度。得到的保留系数控制历史表示并重新加权目标损失。所有样本特定分数均使用训练交互和固定KG离线计算，因此主干模型保持不变，推理时无需访问KG。实验表明，该方法在标准序列推荐器及多个行为去噪序列推荐器上均有性能提升。
英文摘要：
Sequential recommendation predicts the next item from a user's interaction history, but not every interaction is equally informative. Real logs combine persistent preferences with temporary needs, exploration, and incidental behavior, so some interactions can distort history representations or provide unreliable supervision. Existing denoising methods judge such interactions mainly from co-occurrence, order, or model predictions, without explicit evidence from relations between items. Knowledge graphs (KGs) offer this evidence, but item popularity, graph degree, uneven coverage, and widely shared entities can inflate connectivity and bias reliability estimates. Here we present AdaptedKG, which derives calibrated KG evidence for each training example without adding graph representations to the recommendation model. It first compares the observed context with structurally matched alternatives to identify relational paths that are unusually prominent and uses them to build a local KG view. It then compares each interaction with structurally matched reference items to calibrate its support within that view. The resulting retention coefficients gate historical representations and reweight target losses. All sample-specific scores are computed offline using training interactions and a fixed KG, so the backbone remains unchanged and no KG access is required at inference. Experiments show gains with a standard sequential recommender and multiple behavior-denoising sequential recommenders.
