简化、分解或简单：学习用于CTR预测的最佳特征交互方法
Memorize, Factorize, or be Naïve: Learning Optimal Feature Interaction Methods for CTR Prediction
摘要：
点击率预测是商业推荐系统的核心任务之一。它的目的是预测用户点击给定用户和项目特征的特定项目的概率。由于特征间的相互作用带来的非线性，它们被广泛用于改善CTR预测模型的性能。因此，有效地建模特征交互在研究和工业领域都引起了广泛的关注。目前的方法通常可以分为三类：（1）朴素方法，不对特征交互进行建模，只使用原始特征;（2）记忆方法，通过显式地将特征交互视为新特征并分配可训练的嵌入来记忆特征交互;（3）因子分解方法，通过因子分解函数学习原始特征的潜在向量并隐式地对特征交互进行建模。研究表明，由于不同特征相互作用的独特特性，单独使用其中一种方法对特征相互作用进行建模是次优的。为了解决这个问题，我们首先提出了一个通用的框架，称为OptInter，找到最合适的建模方法，为每个功能的相互作用。不同的最先进的深度CTR模型可以被视为OptInter的实例。为了实现OptInter的功能，我们还引入了一个学习算法，自动搜索最佳建模方法。我们在四个大型数据集上进行了广泛的实验。我们的实验表明，OptInter将性能最佳的最先进的基线深度CTR模型提高了2.21%。与记忆方法相比，它也优于基线，我们减少了高达91%的参数。此外，我们还进行了几项消融研究，以调查OptInter不同组件的影响。最后，我们提供了可解释的讨论结果的OptInter。
英文摘要：
Click-through rate prediction is one of the core tasks in commercial recommender systems. It aims to predict the probability of a user clicking a particular item given user and item features. As feature interactions bring in non-linearity, they are widely adopted to improve the performance of CTR prediction models. Therefore, effectively modelling feature interactions has attracted much attention in both the research and industry field. The current approaches can generally be categorized into three classes: (1) naïve methods, which do not model feature interactions and only use original features; (2) memorized methods, which memorize feature interactions by explicitly viewing them as new features and assigning trainable embeddings; (3) factorized methods, which learn latent vectors for original features and implicitly model feature interactions through factorization functions. Studies have shown that modelling feature interactions by one of these methods alone are suboptimal due to the unique characteristics of different feature interactions. To address this issue, we first propose a general framework called OptInter which finds the most suitable modelling method for each feature interaction. Different state-of-the-art deep CTR models can be viewed as instances of OptInter. To realize the functionality of OptInter, we also introduce a learning algorithm that automatically searches for the optimal modelling method. We conduct extensive experiments on four large datasets. Our experiments show that OptInter improves the best performed state-of-the-art baseline deep CTR models by up to 2.21%. Compared to the memorized method, which also outperforms baselines, we reduce up to 91% parameters. In addition, we conduct several ablation studies to investigate the influence of different components of OptInter. Finally, we provide interpretable discussions on the results of OptInter.
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。
