Fast Adaptation for Cold-start Collaborative Filtering with Meta-learning
Fast Adaptation for Cold-start Collaborative Filtering with Meta-learning
复制标题
DOI：
10.1109/icdm50108.2020.00075
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Tianxin Wei;Ziwei Wu;Ruirui Li;Ziniu Hu;Fuli Feng;Xiangnan He;Yizhou Sun;Wei Wang-
中科院分区：
文献类型：
--
作者：
Tianxin Wei;Ziwei Wu;Ruirui Li;Ziniu Hu;Fuli Feng;Xiangnan He;Yizhou Sun;Wei Wang-
协同过滤（CF）作为最流行的方法之一，广泛应用于推荐系统中，但存在冷启动问题，系统中新用户的交互非常有限。为了解决这个问题，以前的工作主要集中在利用各种辅助信息（例如用户个人资料和社交关系）来推断用户偏好。然而，由于用户隐私问题等原因，辅助信息并不总是可用，使得CF方法不得不依靠有限的交互。此外，现实世界的情况需要为新到达的用户动态地提供准确和快速的推荐。因此，在 CF 模型的训练过程中让新用户快速学习至关重要。在本文中，我们提出了一种新颖的学习范式，名为 MetaCF，来学习准确的 CF 模型，该模型可以在有限的交互下快速适应新用户。受元学习的启发，MetaCF 将新用户的快速适应视为一项任务，旨在学习合适的模型来初始化适应。为了追求良好的通用模型，MetaCF 配备了动态子图采样，通过为现有用户动态生成代表性适应任务来考虑新用户的动态到达。此外，为了稳定面临训练样本短缺的适应过程，MetaCF进一步以细粒度的方式优化了适应的学习率。 MetaCF 适用于任何基于 CF 的可微分模型，我们在两个代表性模型 FISM [1] 和 NGCF [2] 上进行了演示。对三个数据集的广泛实验验证了所提出的框架的有效性，该框架在用户-项目交互受到限制的冷启动场景中大大优于最先进的基线。
Collaborative Filtering (CF), as one of the most popular approaches, is widely employed in recommender systems but suffers from the cold-start problem, where interactions are very limited for new users in the system. To deal with this issue, previous work has largely focused on utilizing various auxiliary information such as user profiles and social relationships to infer user preferences. However, the auxiliary information is not always available due to reasons such as user privacy concerns, making the CF approaches have to count on the limited interactions. Moreover, real-world situations require both accurate and quick recommendations for newly arrived users dynamically. Therefore, it is of critical importance to enable fast learning for new users during the training time of CF models. In this paper, we present a novel learning paradigm, named MetaCF, to learn an accurate CF model that makes fast adaptation on new users with limited interactions. Inspired by meta-learning, MetaCF treats the fast adaptation on a new user as a task and aims to learn a suitable model for initializing the adaption. To pursue a well-generalized model, MetaCF is equipped with a Dynamic Subgraph Sampling that accounts for the dynamic arrival of new users by dynamically generating representative adaptation tasks for existing users. Moreover, to stabilize the adaption procedure that faces the shortage of training samples, MetaCF further optimizes the learning rates for adaption in a fine-grained manner. MetaCF is applicable to any differentiable CF-based models where we demonstrate it on two representative ones, FISM [1] and NGCF [2]. Extensive experiments on three datasets validate the effectiveness of the proposed framework, which significantly outperforms state-of-the-art baselines by a large margin in the cold-start scenario where user-item interactions are limited.