Multi-Feature Extension via Semi-Autoencoder for Personalized Recommendation
Over the past few years, personalized recommendation systems aim to address the problem of information overload to help users achieve useful information and make quick decisions. Recently, due to the benefits of effective representation learning and no labeled data requirements, autoencoder-based mo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/23/12408 |
| _version_ | 1797463584464175104 |
|---|---|
| author | Yishuai Geng Yi Zhu Yun Li Xiaobing Sun Bin Li |
| author_facet | Yishuai Geng Yi Zhu Yun Li Xiaobing Sun Bin Li |
| author_sort | Yishuai Geng |
| collection | DOAJ |
| description | Over the past few years, personalized recommendation systems aim to address the problem of information overload to help users achieve useful information and make quick decisions. Recently, due to the benefits of effective representation learning and no labeled data requirements, autoencoder-based models have commonly been used in recommendation systems. Nonetheless, auxiliary information that can effectively enlarge the feature space is always scarce. Moreover, most existing methods ignore the hidden relations between extended features, which significantly affects the recommendation accuracy. To handle these problems, we propose a Multi-Feature extension method via a Semi-AutoEncoder for personalized recommendation (MFSAE). First, we extract auxiliary information from DBpedia as feature extensions of items. Second, we leverage the LSI model to learn hidden relations on top of item features and embed them into low-dimensional feature vectors. Finally, the resulting feature vectors, combined with the original rating matrix and side information, are fed into a semi-autoencoder for recommendation prediction. We ran comprehensive experiments on the MovieLens datasets. The results demonstrate the effectiveness of MFSAE compared to state-of-the-art methods. |
| first_indexed | 2024-03-09T17:52:49Z |
| format | Article |
| id | doaj.art-ec096dea48c64f28bc4969c1c5d70607 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T17:52:49Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-ec096dea48c64f28bc4969c1c5d706072023-11-24T10:36:00ZengMDPI AGApplied Sciences2076-34172022-12-0112231240810.3390/app122312408Multi-Feature Extension via Semi-Autoencoder for Personalized RecommendationYishuai Geng0Yi Zhu1Yun Li2Xiaobing Sun3Bin Li4School of Information Engineering, Yangzhou University, Yangzhou 225127, ChinaSchool of Information Engineering, Yangzhou University, Yangzhou 225127, ChinaSchool of Information Engineering, Yangzhou University, Yangzhou 225127, ChinaSchool of Information Engineering, Yangzhou University, Yangzhou 225127, ChinaSchool of Information Engineering, Yangzhou University, Yangzhou 225127, ChinaOver the past few years, personalized recommendation systems aim to address the problem of information overload to help users achieve useful information and make quick decisions. Recently, due to the benefits of effective representation learning and no labeled data requirements, autoencoder-based models have commonly been used in recommendation systems. Nonetheless, auxiliary information that can effectively enlarge the feature space is always scarce. Moreover, most existing methods ignore the hidden relations between extended features, which significantly affects the recommendation accuracy. To handle these problems, we propose a Multi-Feature extension method via a Semi-AutoEncoder for personalized recommendation (MFSAE). First, we extract auxiliary information from DBpedia as feature extensions of items. Second, we leverage the LSI model to learn hidden relations on top of item features and embed them into low-dimensional feature vectors. Finally, the resulting feature vectors, combined with the original rating matrix and side information, are fed into a semi-autoencoder for recommendation prediction. We ran comprehensive experiments on the MovieLens datasets. The results demonstrate the effectiveness of MFSAE compared to state-of-the-art methods.https://www.mdpi.com/2076-3417/12/23/12408multi-feature extensionautoencoderpersonalized recommendationcollaborative filteringknowledge graph |
| spellingShingle | Yishuai Geng Yi Zhu Yun Li Xiaobing Sun Bin Li Multi-Feature Extension via Semi-Autoencoder for Personalized Recommendation Applied Sciences multi-feature extension autoencoder personalized recommendation collaborative filtering knowledge graph |
| title | Multi-Feature Extension via Semi-Autoencoder for Personalized Recommendation |
| title_full | Multi-Feature Extension via Semi-Autoencoder for Personalized Recommendation |
| title_fullStr | Multi-Feature Extension via Semi-Autoencoder for Personalized Recommendation |
| title_full_unstemmed | Multi-Feature Extension via Semi-Autoencoder for Personalized Recommendation |
| title_short | Multi-Feature Extension via Semi-Autoencoder for Personalized Recommendation |
| title_sort | multi feature extension via semi autoencoder for personalized recommendation |
| topic | multi-feature extension autoencoder personalized recommendation collaborative filtering knowledge graph |
| url | https://www.mdpi.com/2076-3417/12/23/12408 |
| work_keys_str_mv | AT yishuaigeng multifeatureextensionviasemiautoencoderforpersonalizedrecommendation AT yizhu multifeatureextensionviasemiautoencoderforpersonalizedrecommendation AT yunli multifeatureextensionviasemiautoencoderforpersonalizedrecommendation AT xiaobingsun multifeatureextensionviasemiautoencoderforpersonalizedrecommendation AT binli multifeatureextensionviasemiautoencoderforpersonalizedrecommendation |