With the outbreak of today's streaming data, the sequential recommendation is a promising solution to achieve time-aware personalized modeling. It aims to infer the next interacted item of a given user based on the history item sequence. Some recent works tend to improve the sequential recommendation via random masking on the history item so as to generate self-supervised signals. But such approaches will indeed result in sparser item sequence and unreliable signals. Besides, the existing sequential recommendation models are only user-centric, i.e., based on the historical items by chronological order to predict the probability of candidate items, which ignores whether the items from a provider can be successfully recommended. Such user-centric recommendation will make it impossible for the provider to expose their new items and result in popular bias. In this paper, we propose a novel Dual Contrastive Network (DCN) to generate ground-truth self-supervised signals for sequential recommendation by auxiliary user-sequence from an item-centric perspective. Specifically, we propose dual representation contrastive learning to refine the representation learning by minimizing the Euclidean distance between the representations of a given user/item and history items/users of them. Before the second contrastive learning module, we perform the next user prediction to capture the trends of items preferred by certain types of users and provide personalized exploration opportunities for item providers. Finally, we further propose dual interest contrastive learning to self-supervise the dynamic interest from the next item/user prediction and static interest of matching probability. Experiments on four benchmark datasets verify the effectiveness of our proposed method. Further ablation study also illustrates the boosting effect of the proposed components upon different sequential models.

翻译：随着当今流式数据的爆发，序列推荐成为实现时间感知个性化建模的有效方案，旨在根据用户历史交互序列预测其下一个交互物品。近期研究倾向于通过随机掩码历史物品生成自监督信号以改进序列推荐，但此类方法会导致物品序列稀疏化及信号不可靠。此外，现有序列推荐模型仅以用户为中心——即依据时间顺序排列的历史物品预测候选物品概率，忽略了物品提供方的推荐成功率。这种用户中心化推荐会阻碍提供方新物品的曝光，并引发流行度偏差。本文提出新型双视角对比网络（DCN），通过物品视角的辅助用户序列为序列推荐生成真实自监督信号。具体而言，我们提出双表征对比学习，通过最小化给定用户/物品与其历史物品/用户表征之间的欧氏距离来优化表征学习。在第二对比学习模块前，我们执行下一用户预测以捕获特定用户群体偏好的物品趋势，为物品提供方提供个性化探索机会。最后，我们进一步提出双兴趣对比学习，通过下一物品/用户预测的动态兴趣与匹配概率的静态兴趣实现自监督。四个基准数据集上的实验验证了所提方法的有效性，消融研究亦表明各组件对不同序列模型的增强效果。