arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.01473cs.IRcs.LG
收藏

一种基于铰链损耗的跨域推荐码本传输算法

A Hinge-Loss based Codebook Transfer for Cross-Domain Recommendation with Nonoverlapping Data

Mahindra University(马恒达大学);University of Delhi(德里大学);University of Hyderabad(海得拉巴大学)

Sowmini Devi Veeramachaneni, Arun K Pujari, Vineet Padmanabhan, Vikas Kumar

摘要:

推荐系统,特别是基于协同过滤的推荐系统,在电子商务应用中发挥着重要的作用。随着互联网上搜索的信息迅速增加,用户往往面临着寻找自己感兴趣的项目的困难,RS经常在这些任务中提供帮助。最近的研究表明,随着项目空间的增加,以及用户评分的项目数量变得非常少,出现了稀疏性等问题。为了减轻稀疏性问题,正在使用迁移学习技术,其中考虑来自密集域(源)的数据以便预测稀疏域(目标)中的缺失条目。在本文中,我们提出了一个迁移学习方法跨域推荐时,两个领域没有重叠的用户和项目。在我们的方法中,知识从源到目标域的转移是以一种新颖的方式完成的。我们利用共聚类技术来获得源域的码本(聚类等级模式)。利用铰链损失函数将源域的学习码书传递到目标域。使用铰链损失作为损失函数是新颖的,并且在迁移学习中之前没有尝试过。我们证明,我们的技术提高了基准数据集上的目标矩阵的近似。

英文摘要:

Recommender systems(RS), especially collaborative filtering(CF) based RS, has been playing an important role in many e-commerce applications. As the information being searched over the internet is rapidly increasing, users often face the difficulty of finding items of his/her own interest and RS often provides help in such tasks. Recent studies show that, as the item space increases, and the number of items rated by the users become very less, issues like sparsity arise. To mitigate the sparsity problem, transfer learning techniques are being used wherein the data from dense domain(source) is considered in order to predict the missing entries in the sparse domain(target). In this paper, we propose a transfer learning approach for cross-domain recommendation when both domains have no overlap of users and items. In our approach the transferring of knowledge from source to target domain is done in a novel way. We make use of co-clustering technique to obtain the codebook (cluster-level rating pattern) of source domain. By making use of hinge loss function we transfer the learnt codebook of the source domain to target. The use of hinge loss as a loss function is novel and has not been tried before in transfer learning. We demonstrate that our technique improves the approximation of the target matrix on benchmark datasets.

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。

↑