Collaborative filtering recommendations based on multi-factor random walks

Guo, Liangmin; Luan, Kaixuan; Li, Sun; Luo, Yonglong; Zheng, Xiaoyao

doi:10.1016/j.engappai.2023.106409

Cited by 4 publications

(3 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang and Hou (2021) proposed a CF-based book recommendation method, considering the book's interest as an important measure, including factors like search frequency, borrowing time, borrowing frequency, borrowing interval, and renewal frequency. Guo et al (2023) proposed a recommendation method based on multi-factor random walk (MFRW), where MFRW calculated the current user's comprehensive trust value toward other users based on common friends, enhancing recommendation accuracy. Yin et al (2022) proposed a multimodal recommendation model that employed a dual attention mechanism to quantify investor preferences, used deep networks to learn project features, and combined CF mechanisms to model both aspects.…”

Section: Single Domain Book Recommendationmentioning

confidence: 99%

See 1 more Smart Citation

A Cross-Domain Recommender System for Literary Books Using Multi-Head Self-Attention Interaction and Knowledge Transfer Learning

Cui,

Duan,

Zhang

et al. 2023

International Journal of Data Warehousing and Mining

View full text Add to dashboard Cite

Existing book recommendation methods often overlook the rich information contained in the comment text, which can limit their effectiveness. Therefore, a cross-domain recommender system for literary books that leverages multi-head self-attention interaction and knowledge transfer learning is proposed. Firstly, the BERT model is employed to obtain word vectors, and CNN is used to extract user and project features. Then, higher-level features are captured through the fusion of multi-head self-attention and addition pooling. Finally, knowledge transfer learning is introduced to conduct joint modeling between different domains by simultaneously extracting domain-specific features and shared features between domains. On the Amazon dataset, the proposed model achieved MAE and MSE of 0.801 and 1.058 in the “movie-book” recommendation task and 0.787 and 0.805 in the “music-book” recommendation task, respectively. This performance is significantly superior to other advanced recommendation models. Moreover, the proposed model also has good universality on the Chinese dataset.

show abstract

Section: Single Domain Book Recommendationmentioning

confidence: 99%

“…To verify that knowledge transfer learning can improve the recommendation performance of the proposed model, it was compared with two single-domain recommendation models, MF (Ruchitha, 2021) and MFRW (Guo et al, 2023), using only the Movie and Book datasets. The experiment used MAE and MSE as evaluation indicators.…”

Section: Effectiveness Of Knowledge Transfermentioning

confidence: 99%

A Cross-Domain Recommender System for Literary Books Using Multi-Head Self-Attention Interaction and Knowledge Transfer Learning

Cui,

Duan,

Zhang

et al. 2023

International Journal of Data Warehousing and Mining

View full text Add to dashboard Cite

show abstract

“…In the past years, trust-based method [6], random walk-based method [7] and collaborative filtering-based method [8,9] are the classic social recommendation practices. However, all of them take advantage of social relationships based only on lower-order trust relationships, ignoring the influence of potential high-order friends on each other.…”

mentioning

confidence: 99%

SocialCU: Integrating Commonalities and Uniqueness of Users and Items for Social Recommendation

Li,

Gan

2024

Preprint

View full text Add to dashboard Cite

Social recommendation (SR) based on Graph Neural Networks (GNN) presents a promising avenue to significantly improve user experience by leveraging historical behavior and social data, which benefits from capturing user preferences through higher-order relationships. Although two socially connected users will prefer certain specific items, their preferences in other items are likely to be inconsistent. We argue that current GNN-based social recommendation methods only focus on the commonalities of user preferences, but ignore the uniqueness. In addition, GNN also suffers from the data sparsity problem commonly observed in recommender system. To address these limitations, we propose the Integrating Commonalities and Uniqueness of users and items method, namely SocialCU, which combines GNN and contrastive learning to gain commonalities and uniqueness for SR. To be specific, we firstly model the original data as the user-item interaction graph and user-user social graph and use GNN to obtain the commonalities of nodes (users or items). Then, we design the adaptive data augmentation to build dual contrastive learning to refine the uniqueness of nodes and mitigate data sparsity by extracting supervised signals. We have conducted extensive experiments on three real-world datasets to demonstrate the performance advantages of SocialCU over current state-of-the-art recommendation methods and the rationality of the model design.

show abstract