NASM: Nonlinearly Attentive Similarity Model for Recommendation System via Locally Attentive Embedding
Recommendation system, as a core service for many customer-oriented online services, is employed to predict the personalized rating of users on their potentially preferable items. In modern industrial settings, an item-based collaborative filtering (item-based CF) method has been long popular owing...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8715403/ |
| _version_ | 1818737120974471168 |
|---|---|
| author | Zhen-Pei Shan Yun-Qi Lei De-Fu Zhang Jian Zhou |
| author_facet | Zhen-Pei Shan Yun-Qi Lei De-Fu Zhang Jian Zhou |
| author_sort | Zhen-Pei Shan |
| collection | DOAJ |
| description | Recommendation system, as a core service for many customer-oriented online services, is employed to predict the personalized rating of users on their potentially preferable items. In modern industrial settings, an item-based collaborative filtering (item-based CF) method has been long popular owing to its excellent interpretability and high efficiency in the real-time personalized recommendation. In this model, the current target item is recommended according to the interacted similarity from the user's profile, which implies that the key of item-based CF is in the estimation of historical item similarity. Early studies usually utilize statistical measures including cosine similarity and Pearson correlation coefficient to estimate similarity with low accuracy caused by lacking optimization tailed. Recently, there are some learning-based models attempting to learn item similarity by optimizing a recommendation-aware loss function. However, these efforts are mainly concentrated on the application of the shallow linear model, and relative works that deploy some deep learning components for item-based CF are scarce. In this paper, we propose a nonlinearly attentive similarity model (NASM) for item-based CF via locally attentive embedding by introducing local attention and novel nonlinear attention to capture local and global item information, simultaneously. The NASM is based on a neural attentive item similarity (NAIS) model and further achieves significantly superior performance. The experimental results demonstrate that the NASM achieves more competitive recommendation performance in terms of hit ration (HR) and the normalized discounted cumulative gain (NDGC) in comparison with other state-of-the-art recommendation models. |
| first_indexed | 2024-12-18T00:48:00Z |
| format | Article |
| id | doaj.art-b418643dade34255a6f1cd238dec9d12 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T00:48:00Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b418643dade34255a6f1cd238dec9d122022-12-21T21:26:44ZengIEEEIEEE Access2169-35362019-01-017706897070010.1109/ACCESS.2019.29169388715403NASM: Nonlinearly Attentive Similarity Model for Recommendation System via Locally Attentive EmbeddingZhen-Pei Shan0https://orcid.org/0000-0002-1346-3472Yun-Qi Lei1De-Fu Zhang2Jian Zhou3School of Information Science and Engineering, Xiamen University, Xiamen, ChinaSchool of Information Science and Engineering, Xiamen University, Xiamen, ChinaSchool of Information Science and Engineering, Xiamen University, Xiamen, ChinaSchool of Computer Science and Technology, Dalian University of Technology, Dalian, ChinaRecommendation system, as a core service for many customer-oriented online services, is employed to predict the personalized rating of users on their potentially preferable items. In modern industrial settings, an item-based collaborative filtering (item-based CF) method has been long popular owing to its excellent interpretability and high efficiency in the real-time personalized recommendation. In this model, the current target item is recommended according to the interacted similarity from the user's profile, which implies that the key of item-based CF is in the estimation of historical item similarity. Early studies usually utilize statistical measures including cosine similarity and Pearson correlation coefficient to estimate similarity with low accuracy caused by lacking optimization tailed. Recently, there are some learning-based models attempting to learn item similarity by optimizing a recommendation-aware loss function. However, these efforts are mainly concentrated on the application of the shallow linear model, and relative works that deploy some deep learning components for item-based CF are scarce. In this paper, we propose a nonlinearly attentive similarity model (NASM) for item-based CF via locally attentive embedding by introducing local attention and novel nonlinear attention to capture local and global item information, simultaneously. The NASM is based on a neural attentive item similarity (NAIS) model and further achieves significantly superior performance. The experimental results demonstrate that the NASM achieves more competitive recommendation performance in terms of hit ration (HR) and the normalized discounted cumulative gain (NDGC) in comparison with other state-of-the-art recommendation models.https://ieeexplore.ieee.org/document/8715403/Locally historical informationglobally historical informationnonlinearly attentive layerlocally attentive layersimilarity model |
| spellingShingle | Zhen-Pei Shan Yun-Qi Lei De-Fu Zhang Jian Zhou NASM: Nonlinearly Attentive Similarity Model for Recommendation System via Locally Attentive Embedding IEEE Access Locally historical information globally historical information nonlinearly attentive layer locally attentive layer similarity model |
| title | NASM: Nonlinearly Attentive Similarity Model for Recommendation System via Locally Attentive Embedding |
| title_full | NASM: Nonlinearly Attentive Similarity Model for Recommendation System via Locally Attentive Embedding |
| title_fullStr | NASM: Nonlinearly Attentive Similarity Model for Recommendation System via Locally Attentive Embedding |
| title_full_unstemmed | NASM: Nonlinearly Attentive Similarity Model for Recommendation System via Locally Attentive Embedding |
| title_short | NASM: Nonlinearly Attentive Similarity Model for Recommendation System via Locally Attentive Embedding |
| title_sort | nasm nonlinearly attentive similarity model for recommendation system via locally attentive embedding |
| topic | Locally historical information globally historical information nonlinearly attentive layer locally attentive layer similarity model |
| url | https://ieeexplore.ieee.org/document/8715403/ |
| work_keys_str_mv | AT zhenpeishan nasmnonlinearlyattentivesimilaritymodelforrecommendationsystemvialocallyattentiveembedding AT yunqilei nasmnonlinearlyattentivesimilaritymodelforrecommendationsystemvialocallyattentiveembedding AT defuzhang nasmnonlinearlyattentivesimilaritymodelforrecommendationsystemvialocallyattentiveembedding AT jianzhou nasmnonlinearlyattentivesimilaritymodelforrecommendationsystemvialocallyattentiveembedding |