CFMM model framework.
<div><p>Recommendation systems play a significant role in information presentation and research. In particular, goods recommendations for consumers should match consumer psychology, speed up product search, and improve the efficiency of product transactions. Online platforms provide prod...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852018781177511936 |
|---|---|
| author | Chong Zhang (418677) |
| author2 | ZhiCai Zhang (21647998) |
| author2_role | author |
| author_facet | Chong Zhang (418677) ZhiCai Zhang (21647998) |
| author_role | author |
| dc.creator.none.fl_str_mv | Chong Zhang (418677) ZhiCai Zhang (21647998) |
| dc.date.none.fl_str_mv | 2025-07-02T17:57:53Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0327663.g001 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/CFMM_model_framework_/29463847 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Biotechnology Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified world datasets along multiple ablation studies match consumer psychology experimental results show interactive modeling effect fusion loss function existing multimedia algorithms deeply integrating product achieve deep fusion existing algorithms interactive information fusion module feature fusion user information three real significant role recommender systems product transactions product search multimodal information method realizes method adds maximum improvement integration method information presentation information must include product goods recommendations extensive experiments different modules different modalities deeper integration activated multi |
| dc.title.none.fl_str_mv | CFMM model framework. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Recommendation systems play a significant role in information presentation and research. In particular, goods recommendations for consumers should match consumer psychology, speed up product search, and improve the efficiency of product transactions. Online platforms provide product information and interactive information between customers and products. However, the interactive modeling effect of the existing multimedia algorithms on this information must be improved, for instance, by deeply integrating product and interactive information. Accordingly, we propose a cross-fusion-activated multi-modal (CFMM) integration method for recommender systems to achieve deep fusion of product and user information. This method adds a cross-fusion module to fuse the features of different modalities through deep-feature fusion. A fusion loss function is further proposed to improve the recommendation performance of the network. Extensive experiments were conducted on three real-world datasets along with multiple ablation studies to illustrate the effects of the different modules. The experimental results show that the proposed method exhibits better recommendation performance, providing a maximum improvement of 3.8% in the recommendation performance metrics Recall@20, NDCG@20, and Precision@20 in comparisons with existing algorithms. This method realizes a deeper integration of multimodal information; however, the performance can be further improved by extending the multimodal information interaction algorithm to include product and user information.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_089e77c26b60d3d4e14fbc8a0f7eb487 |
| identifier_str_mv | 10.1371/journal.pone.0327663.g001 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/29463847 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | CFMM model framework.Chong Zhang (418677)ZhiCai Zhang (21647998)BiotechnologyScience PolicyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedworld datasets alongmultiple ablation studiesmatch consumer psychologyexperimental results showinteractive modeling effectfusion loss functionexisting multimedia algorithmsdeeply integrating productachieve deep fusionexisting algorithmsinteractive informationfusion modulefeature fusionuser informationthree realsignificant rolerecommender systemsproduct transactionsproduct searchmultimodal informationmethod realizesmethod addsmaximum improvementintegration methodinformation presentationinformation mustinclude productgoods recommendationsextensive experimentsdifferent modulesdifferent modalitiesdeeper integrationactivated multi<div><p>Recommendation systems play a significant role in information presentation and research. In particular, goods recommendations for consumers should match consumer psychology, speed up product search, and improve the efficiency of product transactions. Online platforms provide product information and interactive information between customers and products. However, the interactive modeling effect of the existing multimedia algorithms on this information must be improved, for instance, by deeply integrating product and interactive information. Accordingly, we propose a cross-fusion-activated multi-modal (CFMM) integration method for recommender systems to achieve deep fusion of product and user information. This method adds a cross-fusion module to fuse the features of different modalities through deep-feature fusion. A fusion loss function is further proposed to improve the recommendation performance of the network. Extensive experiments were conducted on three real-world datasets along with multiple ablation studies to illustrate the effects of the different modules. The experimental results show that the proposed method exhibits better recommendation performance, providing a maximum improvement of 3.8% in the recommendation performance metrics Recall@20, NDCG@20, and Precision@20 in comparisons with existing algorithms. This method realizes a deeper integration of multimodal information; however, the performance can be further improved by extending the multimodal information interaction algorithm to include product and user information.</p></div>2025-07-02T17:57:53ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0327663.g001https://figshare.com/articles/figure/CFMM_model_framework_/29463847CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/294638472025-07-02T17:57:53Z |
| spellingShingle | CFMM model framework. Chong Zhang (418677) Biotechnology Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified world datasets along multiple ablation studies match consumer psychology experimental results show interactive modeling effect fusion loss function existing multimedia algorithms deeply integrating product achieve deep fusion existing algorithms interactive information fusion module feature fusion user information three real significant role recommender systems product transactions product search multimodal information method realizes method adds maximum improvement integration method information presentation information must include product goods recommendations extensive experiments different modules different modalities deeper integration activated multi |
| status_str | publishedVersion |
| title | CFMM model framework. |
| title_full | CFMM model framework. |
| title_fullStr | CFMM model framework. |
| title_full_unstemmed | CFMM model framework. |
| title_short | CFMM model framework. |
| title_sort | CFMM model framework. |
| topic | Biotechnology Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified world datasets along multiple ablation studies match consumer psychology experimental results show interactive modeling effect fusion loss function existing multimedia algorithms deeply integrating product achieve deep fusion existing algorithms interactive information fusion module feature fusion user information three real significant role recommender systems product transactions product search multimodal information method realizes method adds maximum improvement integration method information presentation information must include product goods recommendations extensive experiments different modules different modalities deeper integration activated multi |