A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations
A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations
复制标题
DOI：
10.48550/arxiv.2204.00970
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
K. Neupane;Ervine Zheng;Yu Kong;Qi Yu
中科院分区：
文献类型：
--
作者：
K. Neupane;Ervine Zheng;Yu Kong;Qi Yu
我们提出了一种新的动态推荐模型，专注于用户谁在过去的互动，但最近变得相对不活跃。对这些时间敏感的冷启动用户进行有效的推荐对于保持推荐系统的用户群至关重要。由于稀疏的最近的交互，它是具有挑战性的，以捕捉这些用户的当前偏好精确。仅仅依靠他们的历史互动也可能导致过时的建议与他们最近的利益不一致。该模型利用历史和当前的用户项交互，并动态地将用户的（潜在的）偏好分解为特定于时间和时间演变的表示，共同影响用户的行为。这些潜在因素进一步与优化的项目嵌入交互，以实现准确和及时的推荐。在真实数据上的实验证明了所提出的时间敏感的冷启动推荐模型的有效性。
We present a novel dynamic recommendation model that focuses on users who have interactions in the past but turn relatively inactive recently. Making effective recommendations to these time-sensitive cold-start users is critical to maintain the user base of a recommender system. Due to the sparse recent interactions, it is challenging to capture these users' current preferences precisely. Solely relying on their historical interactions may also lead to outdated recommendations misaligned with their recent interests. The proposed model leverages historical and current user-item interactions and dynamically factorizes a user's (latent) preference into time-specific and time-evolving representations that jointly affect user behaviors. These latent factors further interact with an optimized item embedding to achieve accurate and timely recommendations. Experiments over real-world data help demonstrate the effectiveness of the proposed time-sensitive cold-start recommendation model.