[论文解读] Contrastive Self-supervised Sequential Recommendation with Robust Augmentation

Zhiwei Liu, Yongjun Chen+4 more|arXiv (Cornell University)|Aug 14, 2021

Recommender Systems and Techniques参考文献 57被引用 83

一句话总结

本论文提出 CoSeRec，一种对比自监督框架用于序列推荐，使用信息性序列增强以提高对数据稀疏和噪声的鲁棒性，并与下一个项预测共同训练。

ABSTRACT

Sequential Recommendationdescribes a set of techniques to model dynamic user behavior in order to predict future interactions in sequential user data. At their core, such approaches model transition probabilities between items in a sequence, whether through Markov chains, recurrent networks, or more recently, Transformers. However both old and new issues remain, including data-sparsity and noisy data; such issues can impair the performance, especially in complex, parameter-hungry models. In this paper, we investigate the application of contrastive Self-Supervised Learning (SSL) to the sequential recommendation, as a way to alleviate some of these issues. Contrastive SSL constructs augmentations from unlabelled instances, where agreements among positive pairs are maximized. It is challenging to devise a contrastive SSL framework for a sequential recommendation, due to its discrete nature, correlations among items, and skewness of length distributions. To this end, we propose a novel framework, Contrastive Self-supervised Learning for sequential Recommendation (CoSeRec). We introduce two informative augmentation operators leveraging item correlations to create high-quality views for contrastive learning. Experimental results on three real-world datasets demonstrate the effectiveness of the proposed method on improving model performance and the robustness against sparse and noisy data. Our implementation is available online at \url{https://github.com/YChen1993/CoSeRec}

研究动机与目标

• 动机并解决序列推荐（SR）中的数据稀疏性和噪声交互问题。
• 引入保留项相关性并处理长度偏斜的信息性序列增强。
• 提出对比自监督学习目标和多任务训练策略，以联合优化 SR 和 SSL。

提出的方法

• 提出两种信息性增强算子—替换（S）和插入（I）—利用项之间的相关性来创建鲁棒的视图。
• 将基于记忆的和基于模型的项相关性结合起来，融合成用于增强选择的混合相关性 Cor_h。
• 采用三种随机增强（裁剪 Crop、掩码 Mask、重新排序 Reorder），并按序列长度定制增强集合以支持短序列。
• 使用 NT-Xent 对比损失最大化同一序列的两个增强视图之间的一致性。
• 用一个多任务目标训练 SR 编码器，将下一个项预测损失与 ssl 损失结合起来，并使用平衡超参数 lambda。

实验结果

研究问题

• RQ1 与现有方法相比，CoSeRec 在 SR 上的表现如何？
• RQ2 哪些增强策略最适合 SR，信息性增强对性能有何影响？
• RQ3 CoSeRec 能否对 SR 中的稀疏数据和噪声交互具有鲁棒性？
• RQ4 不同的超参数和增强配置如何影响 CoSeRec？

主要发现

• CoSeRec 在三个真实世界数据集上在 HR@k 和 NDCG@k 指标上持续优于基线模型。
• 利用项相关性的的信息性增强提升正向视图质量并缓解冷启动问题，尤其是对短序列。
• 联合多任务训练（SR+SSL）的性能优于先做两阶段预训练再进行 SR 微调。
• 用于选择相关项的混合相关性（Cor_h）随着训练进行可提升增强鲁棒性。