A List-Ranking Framework Based on Linear and Non-Linear Fusion for Recommendation from Implicit Feedback
Although most list-ranking frameworks are based on multilayer perceptrons (MLP), they still face limitations within the method itself in the field of recommender systems in two respects: (1) MLP suffer from overfitting when dealing with sparse vectors. At the same time, the model itself tends to lea...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/24/6/778 |
| _version_ | 1797487690411671552 |
|---|---|
| author | Buchen Wu Jiwei Qin |
| author_facet | Buchen Wu Jiwei Qin |
| author_sort | Buchen Wu |
| collection | DOAJ |
| description | Although most list-ranking frameworks are based on multilayer perceptrons (MLP), they still face limitations within the method itself in the field of recommender systems in two respects: (1) MLP suffer from overfitting when dealing with sparse vectors. At the same time, the model itself tends to learn in-depth features of user–item interaction behavior but ignores some low-rank and shallow information present in the matrix. (2) Existing ranking methods cannot effectively deal with the problem of ranking between items with the same rating value and the problem of inconsistent independence in reality. We propose a list ranking framework based on linear and non-linear fusion for recommendation from implicit feedback, named RBLF. First, the model uses dense vectors to represent users and items through one-hot encoding and embedding. Second, to jointly learn shallow and deep user–item interaction, we use the interaction grabbing layer to capture the user–item interaction behavior through dense vectors of users and items. Finally, RBLF uses the Bayesian collaborative ranking to better fit the characteristics of implicit feedback. Eventually, the experiments show that the performance of RBLF obtains a significant improvement. |
| first_indexed | 2024-03-09T23:51:20Z |
| format | Article |
| id | doaj.art-2120adbc253349728dc47444599cd34f |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-09T23:51:20Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-2120adbc253349728dc47444599cd34f2023-11-23T16:32:59ZengMDPI AGEntropy1099-43002022-05-0124677810.3390/e24060778A List-Ranking Framework Based on Linear and Non-Linear Fusion for Recommendation from Implicit FeedbackBuchen Wu0Jiwei Qin1School of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaSchool of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaAlthough most list-ranking frameworks are based on multilayer perceptrons (MLP), they still face limitations within the method itself in the field of recommender systems in two respects: (1) MLP suffer from overfitting when dealing with sparse vectors. At the same time, the model itself tends to learn in-depth features of user–item interaction behavior but ignores some low-rank and shallow information present in the matrix. (2) Existing ranking methods cannot effectively deal with the problem of ranking between items with the same rating value and the problem of inconsistent independence in reality. We propose a list ranking framework based on linear and non-linear fusion for recommendation from implicit feedback, named RBLF. First, the model uses dense vectors to represent users and items through one-hot encoding and embedding. Second, to jointly learn shallow and deep user–item interaction, we use the interaction grabbing layer to capture the user–item interaction behavior through dense vectors of users and items. Finally, RBLF uses the Bayesian collaborative ranking to better fit the characteristics of implicit feedback. Eventually, the experiments show that the performance of RBLF obtains a significant improvement.https://www.mdpi.com/1099-4300/24/6/778multilayer perceptronscollaborative filteringlist ranking |
| spellingShingle | Buchen Wu Jiwei Qin A List-Ranking Framework Based on Linear and Non-Linear Fusion for Recommendation from Implicit Feedback Entropy multilayer perceptrons collaborative filtering list ranking |
| title | A List-Ranking Framework Based on Linear and Non-Linear Fusion for Recommendation from Implicit Feedback |
| title_full | A List-Ranking Framework Based on Linear and Non-Linear Fusion for Recommendation from Implicit Feedback |
| title_fullStr | A List-Ranking Framework Based on Linear and Non-Linear Fusion for Recommendation from Implicit Feedback |
| title_full_unstemmed | A List-Ranking Framework Based on Linear and Non-Linear Fusion for Recommendation from Implicit Feedback |
| title_short | A List-Ranking Framework Based on Linear and Non-Linear Fusion for Recommendation from Implicit Feedback |
| title_sort | list ranking framework based on linear and non linear fusion for recommendation from implicit feedback |
| topic | multilayer perceptrons collaborative filtering list ranking |
| url | https://www.mdpi.com/1099-4300/24/6/778 |
| work_keys_str_mv | AT buchenwu alistrankingframeworkbasedonlinearandnonlinearfusionforrecommendationfromimplicitfeedback AT jiweiqin alistrankingframeworkbasedonlinearandnonlinearfusionforrecommendationfromimplicitfeedback AT buchenwu listrankingframeworkbasedonlinearandnonlinearfusionforrecommendationfromimplicitfeedback AT jiweiqin listrankingframeworkbasedonlinearandnonlinearfusionforrecommendationfromimplicitfeedback |