Effective metric learning with co-occurrence embedding for collaborative recommendations
Effective metric learning with co-occurrence embedding for collaborative recommendations
复制标题
通过共现嵌入进行有效的度量学习以实现协作推荐
DOI：
10.1016/j.neunet.2020.01.021
复制
发表时间：
2020-01
期刊：
影响因子：
7.8
通讯作者：
Cao Jinde
中科院分区：
文献类型：
--
作者：
Wu Hao;Zhou Qimin;Nie Rencan;Cao Jinde
在推荐系统中，矩阵分解及其变体由于其简单性和有效性而成为协同过滤中协同推荐的有效度量学习与同现嵌入。在基于矩阵分解的推荐方法中，点积实际上被用作从用户到项目的距离的度量，不满足不等式性质，因此可能无法捕获内部粒度的偏好信息，并进一步限制推荐的性能。度量学习产生的距离函数，捕捉评级数据之间的基本关系，并已成功地探索在协作推荐。然而，没有用户-用户对和项目-项目对的全局统计信息，这使得模型很容易实现次优度量。为此，我们提出了一个同现嵌入正则化度量学习模型（CRML）的协同推荐。我们认为优化问题是一个多任务学习问题，其中包括优化的度量学习的主要任务和两个辅助任务的表示学习。特别是，我们开发了一种有效的方法来学习用户和项目的嵌入表示，然后利用软参数共享的策略来优化模型参数。在四个数据集上的实验表明，CRML模型可以增强朴素度量学习模型，在协同推荐的准确性方面明显优于现有方法. (C)2020爱思唯尔有限公司保留所有权利。
In recommender systems, matrix factorization and its variants have grown up to be dominEffective metric learning with co-occurrence embedding for collaborative recommendationsant in collaborative filtering due to their simplicity and effectiveness. In matrix factorization based methods, dot product which is actually used as a measure of distance from users to items, does not satisfy the inequality property, and thus may fail to capture the inner grained preference information and further limits the performance of recommendations. Metric learning produces distance functions that capture the essential relationships among rating data and has been successfully explored in collaborative recommendations. However, without the global statistical information of user-user pairs and item-item pairs, it makes the model easy to achieve a suboptimal metric. For this, we present a cooccurrence embedding regularized metric learning model (CRML) for collaborative recommendations. We consider the optimization problem as a multi-task learning problem which includes optimizing a primary task of metric learning and two auxiliary tasks of representation learning. In particular, we develop an effective approach for learning the embedding representations of both users and items, and then exploit the strategy of soft parameter sharing to optimize the model parameters. Empirical experiments on four datasets demonstrate that the CRML model can enhance the naive metric learning model and significantly outperforms the state-of-the-art methods in terms of accuracy of collaborative recommendations. (C) 2020 Elsevier Ltd. All rights reserved.
登录
查看更多内容
DOI：
10.1145/2959100.2959182
发表时间：
2016-09
期刊：
Proceedings of the 10th ACM Conference on Recommender Systems
影响因子：
--
作者：
Dawen Liang;Jaan Altosaar;Laurent Charlin;D. Blei
通讯作者：
Dawen Liang;Jaan Altosaar;Laurent Charlin;D. Blei
影响因子：
3.4
作者：
Harper, F. Maxwell;Konstan, Joseph A.
通讯作者：
Konstan, Joseph A.
影响因子：
6
作者：
Yang, Xiwang;Guo, Yang;Steck, Harald
通讯作者：
Steck, Harald
影响因子：
6
作者：
L. Maaten;Geoffrey E. Hinton
通讯作者：
L. Maaten;Geoffrey E. Hinton
影响因子：
4.8
作者：
Wang, Fei;Sun, Jimeng
通讯作者：
Sun, Jimeng