Accurate user interest modeling is vital for recommendation scenarios. One of the effective solutions is the sequential recommendation that relies on click behaviors, but this is not elegant in the video feed recommendation where users are passive in receiving the streaming contents and return skip or no-skip behaviors. Here skip and no-skip behaviors can be treated as negative and positive feedback, respectively. With the mixture of positive and negative feedback, it is challenging to capture the transition pattern of behavioral sequence. To do so, FeedRec has exploited a shared vanilla Transformer, which may be inelegant because head interaction of multi-heads attention does not consider different types of feedback. In this paper, we propose Dual-interest Factorization-heads Attention for Sequential Recommendation (short for DFAR) consisting of feedback-aware encoding layer, dual-interest disentangling layer and prediction layer. In the feedback-aware encoding layer, we first suppose each head of multi-heads attention can capture specific feedback relations. Then we further propose factorization-heads attention which can mask specific head interaction and inject feedback information so as to factorize the relation between different types of feedback. Additionally, we propose a dual-interest disentangling layer to decouple positive and negative interests before performing disentanglement on their representations. Finally, we evolve the positive and negative interests by corresponding towers whose outputs are contrastive by BPR loss. Experiments on two real-world datasets show the superiority of our proposed method against state-of-the-art baselines. Further ablation study and visualization also sustain its effectiveness. We release the source code here: https://github.com/tsinghua-fib-lab/WWW2023-DFAR.

翻译：精确的用户兴趣建模对于推荐场景至关重要。一种有效的解决方案是依赖点击行为的序列推荐，但在视频流推荐中这种方法并不优雅，因为用户被动接收流式内容，并返回跳过或不跳过行为。这里跳过和不跳过行为可分别视为负反馈和正反馈。在正负反馈混合的情况下，捕捉行为序列的转换模式具有挑战性。为此，FeedRec采用了一个共享的标准Transformer，这可能不够优雅，因为多头注意力中的头交互并未考虑不同类型的反馈。本文提出面向序列推荐的双重兴趣因子化多头注意力（简称DFAR），由反馈感知编码层、双重兴趣解耦层和预测层组成。在反馈感知编码层中，我们首先假设多头注意力的每个头能捕捉特定的反馈关系。然后进一步提出因子化多头注意力，通过掩码特定头交互并注入反馈信息，从而解耦不同类型反馈之间的关系。此外，我们提出双重兴趣解耦层，在执行表示解耦前先分离正负兴趣。最后，通过对应塔模块演化正负兴趣，其输出通过BPR损失进行对比。在两个真实世界数据集上的实验表明，我们提出的方法优于当前最先进的基线模型。进一步的消融研究和可视化也验证了其有效性。我们在此处公开源代码：https://github.com/tsinghua-fib-lab/WWW2023-DFAR。