Robust Transfer Learning for Cross-domain Collaborative Filtering Using Multiple Rating Patterns Approximation

He, Ming; Zhang, Jiuling; Yang, Peng; Yao, Kaisheng

doi:10.1145/3159652.3159675

Cited by 48 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CST [22] utilizes the user embedding in the source domain to initialize the embedding in the target domain and restricts them from being closed. In recent years, researchers proposed many deep learning-based models to enhance knowledge transfer [5,6,8,31,34,42]. CoNet [8] transfers and combines the knowledge by using cross-connections between feed-forward neural networks.…”

Section: Related Work 21 Cross-domain Recommendationmentioning

confidence: 99%

Personalized Transfer of User Preferences for Cross-domain Recommendation

Zhu

Tang

Liu

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

135

View full text Add to dashboard Cite

Cold-start problem is still a very challenging problem in recommender systems. Fortunately, the interactions of the cold-start users in the auxiliary source domain can help cold-start recommendations in the target domain. How to transfer user's preferences from the source domain to the target domain, is the key issue in Crossdomain Recommendation (CDR) which is a promising solution to deal with the cold-start problem. Most existing methods model a common preference bridge to transfer preferences for all users. Intuitively, since preferences vary from user to user, the preference bridges of different users should be different. Along this line, we propose a novel framework named Personalized Transfer of User Preferences for Cross-domain Recommendation (PTUPCDR). Specifically, a meta network fed with users' characteristic embeddings is learned to generate personalized bridge functions to achieve personalized transfer of preferences for each user. To learn the meta network stably, we employ a task-oriented optimization procedure. With the meta-generated personalized bridge function, the user's preference embedding in the source domain can be transformed into the target domain, and the transformed user preference embedding can be utilized as the initial embedding for the cold-start user in the target domain. Using large real-world datasets, we conduct extensive experiments to evaluate the effectiveness of PTUPCDR on both cold-start and warm-start stages. The code has been available at https://github.com/easezyc/WSDM2022-PTUPCDR.

show abstract

Section: Related Work 21 Cross-domain Recommendationmentioning

confidence: 99%

Personalized Transfer of User Preferences for Cross-domain Recommendation

Zhu

Tang

Liu

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

135

View full text Add to dashboard Cite

show abstract

“…The cross-stitch network [34] and its sparse variant [21] enable information sharing between two base networks for each domain in a deep way. Robust learning is also considered during knowledge transfer [15]. These methods treat knowledge transfer as a global process with shared global parameters and do not match source items with the specific target item given a user.…”

Section: Related Workmentioning

confidence: 99%

Transfer Meets Hybrid: A Synthetic Approach for Cross-Domain Collaborative Filtering with Text

Zhang

Yang

2019

The World Wide Web Conference

View full text Add to dashboard Cite

Collaborative filtering (CF) is the key technique for recommender systems (RSs). CF exploits user-item behavior interactions (e.g., clicks) only and hence suffers from the data sparsity issue. One research thread is to integrate auxiliary information such as product reviews and news titles, leading to hybrid filtering methods. Another thread is to transfer knowledge from other source domains such as improving the movie recommendation with the knowledge from the book domain, leading to transfer learning methods. In real-world life, no single service can satisfy a user's all information needs. Thus it motivates us to exploit both auxiliary and source information for RSs in this paper. We propose a novel neural model to smoothly enable Transfer Meeting Hybrid (TMH) methods for cross-domain recommendation with unstructured text in an end-to-end manner. TMH attentively extracts useful content from unstructured text via a memory module and selectively transfers knowledge from a source domain via a transfer network. On two real-world datasets, TMH shows better performance in terms of three ranking metrics by comparing with various baselines. We conduct thorough analyses to understand how the text content and transferred knowledge help the proposed model.

show abstract

“…Zhang et al borrowed domain adaptation technique to maintain information consistency during the transfer learning process and established cross-domain recommender system with consistent information transfer [26], which could extract consistent knowledge of different domains and improve the recommendation performance. Recently, He et al proposed a robust multiple-rating-pattern transfer learning model [27] which leveraged rating patterns from multiple incomplete source domains to boost the quality of recommender systems.…”

Section: B Cross-domain Cf Algorithmsmentioning

confidence: 99%

An Improved Matrix Approximation for Recommender Systems Based on Context-Information and Transfer Learning

2019

IEEE Access

View full text Add to dashboard Cite

As we all known, transfer learning is an effective way to alleviate the sparsity problem in recommender systems by transferring the shared knowledge cross multiple related domains. However, additional related domain is not always available, and auxiliary data may be noisy and this leads to negative transfer. In this paper, we suppose that different parts of one domain also have the shared knowledge and put forward a novel in-domain collaborative filtering framework, which utilizes contextual information to divide an original user-item interaction matrix into some smaller sub-matrices and regards the selected sub-matrices as ''multiple domains'' to establish transfer learning. The proposed framework no longer needs additional domain information and has a better adaptive ability. Also, considering more actual situation that users may have multiple personalities and items may have diverse attributes, we resort to Rating-Matrix Generative Model (RMGM) to generate the shared cluster-level rating pattern. Experiments on dataset Douban with three different categories demonstrate that the proposed framework can improve the prediction accuracy as well as the top-N recommendation performance.INDEX TERMS Recommender systems, context-aware, transfer learning, in-domain collaborative filtering.

show abstract

Robust Transfer Learning for Cross-domain Collaborative Filtering Using Multiple Rating Patterns Approximation

Cited by 48 publications

References 26 publications

Personalized Transfer of User Preferences for Cross-domain Recommendation

Personalized Transfer of User Preferences for Cross-domain Recommendation

Transfer Meets Hybrid: A Synthetic Approach for Cross-Domain Collaborative Filtering with Text

An Improved Matrix Approximation for Recommender Systems Based on Context-Information and Transfer Learning

Contact Info

Product

Resources

About