Recent years have witnessed the explosive growth of interaction behaviors in multimedia information systems, where multi-behavior recommender systems have received increasing attention by leveraging data from various auxiliary behaviors such as tip and collect. Among various multi-behavior recommendation methods, non-sampling methods have shown superiority over negative sampling methods. However, two observations are usually ignored in existing state-of-the-art non-sampling methods based on binary regression: (1) users have different preference strengths for different items, so they cannot be measured simply by binary implicit data; (2) the dependency across multiple behaviors varies for different users and items. To tackle the above issue, we propose a novel non-sampling learning framework named Criterion-guided Heterogeneous Collaborative Filtering (CHCF). CHCF introduces both upper and lower thresholds to indicate selection criteria, which will guide user preference learning. Besides, CHCF integrates criterion learning and user preference learning into a unified framework, which can be trained jointly for the interaction prediction of the target behavior. We further theoretically demonstrate that the optimization of Collaborative Metric Learning can be approximately achieved by the CHCF learning framework in a non-sampling form effectively. Extensive experiments on three real-world datasets show the effectiveness of CHCF in heterogeneous scenarios.

翻译：近年来，多媒体信息系统中的交互行为呈现爆炸式增长，通过利用诸如打赏和收藏等各类辅助行为的数据，多行为推荐系统受到越来越多的关注。在多种多行为推荐方法中，非采样方法已展现出优于负采样方法的性能。然而，现有最先进的基于二元回归的非采样方法通常忽略两个观察：(1) 用户对不同物品具有不同的偏好强度，因此无法简单通过二元隐式数据衡量；(2) 多行为之间的依赖关系因用户和物品而异。为解决上述问题，我们提出一种新颖的非采样学习框架——准则引导的异质协同过滤（CHCF）。CHCF引入上下阈值来表示选择准则，从而指导用户偏好学习。此外，CHCF将准则学习与用户偏好学习整合到统一框架中，可联合训练以预测目标行为的交互。我们进一步从理论上证明，协同度量学习的优化可通过CHCF学习框架以非采样形式有效近似实现。在三个真实数据集上的广泛实验表明，CHCF在异质场景下具有有效性。