Recently, multi-interest models, which extract interests of a user as multiple representation vectors, have shown promising performances for sequential recommendation. However, none of existing multi-interest recommendation models consider the Out-Of-Distribution (OOD) generalization problem, in which interest distribution may change. Considering multiple interests of a user are usually highly correlated, the model has chance to learn spurious correlations between noisy interests and target items. Once the data distribution changes, the correlations among interests may also change, and the spurious correlations will mislead the model to make wrong predictions. To tackle with above OOD generalization problem, we propose a novel multi-interest network, named DEep Stable Multi-Interest Learning (DESMIL), which attempts to de-correlate the extracted interests in the model, and thus spurious correlations can be eliminated. DESMIL applies an attentive module to extract multiple interests, and then selects the most important one for making final predictions. Meanwhile, DESMIL incorporates a weighted correlation estimation loss based on Hilbert-Schmidt Independence Criterion (HSIC), with which training samples are weighted, to minimize the correlations among extracted interests. Extensive experiments have been conducted under both OOD and random settings, and up to 36.8% and 21.7% relative improvements are achieved respectively.

翻译：近年来，多兴趣模型通过将用户兴趣提取为多个表征向量，在序列推荐中展现了优异性能。然而，现有推荐模型均未考虑兴趣分布可能变化的分布外泛化问题。由于用户的多重兴趣通常高度相关，模型可能学习到噪声兴趣与目标物品之间的虚假关联。当数据分布发生变化时，兴趣间的关联性也可能改变，导致虚假关联误导模型做出错误预测。为解决上述分布外泛化问题，我们提出一种新型多兴趣网络——深度稳定多兴趣学习（DESMIL），该网络通过去相关模型提取的兴趣以消除虚假关联。DESMIL采用注意力模块提取多重兴趣，并选择最重要兴趣进行最终预测。同时，基于希尔伯特-施密特独立性准则（HSIC）引入加权相关性估计损失，通过对训练样本加权来最小化提取兴趣间的相关性。我们在分布外与随机场景下开展大量实验，分别取得了高达36.8%与21.7%的相对性能提升。