用稳定学习改进多兴趣网络
Improving Multi-Interest Network with Stable Learning
摘要:
从用户的历史行为中建模用户的动态偏好是现代推荐系统的核心。由于用户兴趣的多样性,最近的进展提出了多兴趣网络,将历史行为编码成多个兴趣向量。在实际场景中,通常将捕获的兴趣的对应项一起检索以获得曝光并收集到训练数据中,这产生了兴趣之间的依赖性。不幸的是,多兴趣网络可能会错误地集中在所捕获的兴趣之间的微妙依赖关系上。在这些依赖关系的误导下,不相关的兴趣和目标之间的虚假相关性被捕获,导致当训练和测试分布不匹配时预测结果的不稳定。在本文中,我们引入了广泛使用的希尔伯特施密特独立性准则(HSIC)来衡量捕获的利益之间的独立性程度,并实证表明,HSIC的持续增加可能会损害模型的性能。在此基础上,我们提出了一种新的多兴趣网络,称为DESMIL(DEep Stable Multi-Interest Learning),它试图通过学习训练样本的权重来消除捕获的兴趣之间的微妙依赖关系的影响,并使模型更专注于潜在的真实因果关系。我们在公共推荐数据集、大规模工业数据集和模拟分布外数据的合成数据集上进行了广泛的实验。实验结果表明,我们提出的DESMIL优于国家的最先进的模型的显着保证金。此外,我们还进行了全面的模型分析,以揭示为什么DESMIL工作在一定程度上的原因。
英文摘要:
Modeling users' dynamic preferences from historical behaviors lies at the core of modern recommender systems. Due to the diverse nature of user interests, recent advances propose the multi-interest networks to encode historical behaviors into multiple interest vectors. In real scenarios, the corresponding items of captured interests are usually retrieved together to get exposure and collected into training data, which produces dependencies among interests. Unfortunately, multi-interest networks may incorrectly concentrate on subtle dependencies among captured interests. Misled by these dependencies, the spurious correlations between irrelevant interests and targets are captured, resulting in the instability of prediction results when training and test distributions do not match. In this paper, we introduce the widely used Hilbert-Schmidt Independence Criterion (HSIC) to measure the degree of independence among captured interests and empirically show that the continuous increase of HSIC may harm model performance. Based on this, we propose a novel multi-interest network, named DEep Stable Multi-Interest Learning (DESMIL), which tries to eliminate the influence of subtle dependencies among captured interests via learning weights for training samples and make model concentrate more on underlying true causation. We conduct extensive experiments on public recommendation datasets, a large-scale industrial dataset and the synthetic datasets which simulate the out-of-distribution data. Experimental results demonstrate that our proposed DESMIL outperforms state-of-the-art models by a significant margin. Besides, we also conduct comprehensive model analysis to reveal the reason why DESMIL works to a certain extent.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。