[论文解读] Sequential Recommendation with Graph Neural Networks

Jianxin Chang, Chen Gao+6 more|arXiv (Cornell University)|Jun 27, 2021

Recommender Systems and Techniques参考文献 62被引用 20

一句话总结

该论文提出SURGE，一种图神经网络模型，通过将松散的用户行为序列转化为紧密的物品-物品兴趣图，从嘈杂的隐式反馈中提炼核心偏好。通过应用聚类感知图卷积和动态图池化，SURGE有效捕捉了用户兴趣的演化过程，在公开数据集和工业数据集上均实现了最先进性能，尤其在长序列建模方面表现突出。

ABSTRACT

Sequential recommendation aims to leverage users' historical behaviors to predict their next interaction. Existing works have not yet addressed two main challenges in sequential recommendation. First, user behaviors in their rich historical sequences are often implicit and noisy preference signals, they cannot sufficiently reflect users' actual preferences. In addition, users' dynamic preferences often change rapidly over time, and hence it is difficult to capture user patterns in their historical sequences. In this work, we propose a graph neural network model called SURGE (short for SeqUential Recommendation with Graph neural nEtworks) to address these two issues. Specifically, SURGE integrates different types of preferences in long-term user behaviors into clusters in the graph by re-constructing loose item sequences into tight item-item interest graphs based on metric learning. This helps explicitly distinguish users' core interests, by forming dense clusters in the interest graph. Then, we perform cluster-aware and query-aware graph convolutional propagation and graph pooling on the constructed graph. It dynamically fuses and extracts users' current activated core interests from noisy user behavior sequences. We conduct extensive experiments on both public and proprietary industrial datasets. Experimental results demonstrate significant performance gains of our proposed method compared to state-of-the-art methods. Further studies on sequence length confirm that our method can model long behavioral sequences effectively and efficiently.

研究动机与目标

• 解决从长序列、嘈杂的行为序列中建模动态演化用户偏好的挑战。
• 克服现有方法过度依赖近期行为、未能有效利用长期隐式反馈的局限性。
• 提出一种基于图的框架，显式地从隐式信号中聚类并提取用户的内核兴趣。
• 通过将行为序列转化为结构化的兴趣图，实现对长行为序列的有效且高效的建模。

提出的方法

• 通过度量学习重新编码松散的用户行为序列，基于用户交互模式将相似物品分组，构建紧密的物品-物品兴趣图。
• 应用注意力图卷积网络，将弱偏好信号聚合为更强、更具代表性的兴趣聚类。
• 引入聚类感知图卷积，以在每个聚类内传播并优化用户兴趣表征。
• 实现动态图池化，基于查询感知注意力自适应地选择并保留当前激活的核心兴趣。
• 使用可学习注意力机制在推理时加权不同兴趣聚类的重要性，以反映当前用户偏好。
• 端到端训练模型，联合优化兴趣聚类与下一物品预测。

实验结果

研究问题

• RQ1 基于图的方法能否有效从长序列、嘈杂的隐式反馈行为序列中提炼出核心用户兴趣？
• RQ2 图神经网络模型在多大程度上能够捕捉用户偏好随时间的动态演化？
• RQ3 与现有方法相比，将松散行为序列转化为紧密兴趣图是否能提升序列推荐性能？
• RQ4 所提出的方法能否在不导致性能下降的情况下有效建模长行为序列？
• RQ5 动态图池化在预测过程中如何有助于过滤掉不活跃或无关的兴趣？

主要发现

• SURGE在公开数据集和专有工业数据集上均显著优于最先进方法，召回率和精确率指标均有显著提升。
• 在公开的DLRM数据集上，SURGE的recall@20达到0.8906，precision@20达到0.4228，超越了之前的SOTA方法。
• 在专有的快手（Kuaishou）数据集上，SURGE的recall@20达到0.8525，precision@20达到0.9316，展现出在真实世界数据上的强大泛化能力。
• 消融实验确认，图构建和动态池化组件对性能至关重要，尤其在长序列场景下。
• 该模型保持了高效率和可扩展性，在序列长度增加时仍表现出稳定性能。
• 该方法能有效过滤掉嘈杂的非核心偏好，聚焦于当前激活的兴趣，从而实现更准确的下一物品预测。