Efficient Graph Collaborative Filtering via Contrastive Learning
Collaborative filtering (CF) aims to make recommendations for users by detecting user’s preference from the historical user–item interactions. Existing graph neural networks (GNN) based methods achieve satisfactory performance by exploiting the high-order connectivity between users and items, howeve...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/14/4666 |
| _version_ | 1797526055496450048 |
|---|---|
| author | Zhiqiang Pan Honghui Chen |
| author_facet | Zhiqiang Pan Honghui Chen |
| author_sort | Zhiqiang Pan |
| collection | DOAJ |
| description | Collaborative filtering (CF) aims to make recommendations for users by detecting user’s preference from the historical user–item interactions. Existing graph neural networks (GNN) based methods achieve satisfactory performance by exploiting the high-order connectivity between users and items, however they suffer from the poor training efficiency problem and easily introduce bias for information propagation. Moreover, the widely applied Bayesian personalized ranking (BPR) loss is insufficient to provide supervision signals for training due to the extremely sparse observed interactions. To deal with the above issues, we propose the Efficient Graph Collaborative Filtering (EGCF) method. Specifically, EGCF adopts merely one-layer graph convolution to model the collaborative signal for users and items from the first-order neighbors in the user–item interactions. Moreover, we introduce contrastive learning to enhance the representation learning of users and items by deriving the self-supervisions, which is jointly trained with the supervised learning. Extensive experiments are conducted on two benchmark datasets, i.e., Yelp2018 and Amazon-book, and the experimental results demonstrate that EGCF can achieve the state-of-the-art performance in terms of Recall and normalized discounted cumulative gain (NDCG), especially on ranking the target items at right positions. In addition, EGCF shows obvious advantages in the training efficiency compared with the competitive baselines, making it practicable for potential applications. |
| first_indexed | 2024-03-10T09:24:43Z |
| format | Article |
| id | doaj.art-6897cf72bc5a4b58b55b72efa9391c9d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:24:43Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6897cf72bc5a4b58b55b72efa9391c9d2023-11-22T04:54:14ZengMDPI AGSensors1424-82202021-07-012114466610.3390/s21144666Efficient Graph Collaborative Filtering via Contrastive LearningZhiqiang Pan0Honghui Chen1Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaScience and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaCollaborative filtering (CF) aims to make recommendations for users by detecting user’s preference from the historical user–item interactions. Existing graph neural networks (GNN) based methods achieve satisfactory performance by exploiting the high-order connectivity between users and items, however they suffer from the poor training efficiency problem and easily introduce bias for information propagation. Moreover, the widely applied Bayesian personalized ranking (BPR) loss is insufficient to provide supervision signals for training due to the extremely sparse observed interactions. To deal with the above issues, we propose the Efficient Graph Collaborative Filtering (EGCF) method. Specifically, EGCF adopts merely one-layer graph convolution to model the collaborative signal for users and items from the first-order neighbors in the user–item interactions. Moreover, we introduce contrastive learning to enhance the representation learning of users and items by deriving the self-supervisions, which is jointly trained with the supervised learning. Extensive experiments are conducted on two benchmark datasets, i.e., Yelp2018 and Amazon-book, and the experimental results demonstrate that EGCF can achieve the state-of-the-art performance in terms of Recall and normalized discounted cumulative gain (NDCG), especially on ranking the target items at right positions. In addition, EGCF shows obvious advantages in the training efficiency compared with the competitive baselines, making it practicable for potential applications.https://www.mdpi.com/1424-8220/21/14/4666recommender systemsefficient recommendationcollaborative filteringgraph convolution networkscontrastive learning |
| spellingShingle | Zhiqiang Pan Honghui Chen Efficient Graph Collaborative Filtering via Contrastive Learning Sensors recommender systems efficient recommendation collaborative filtering graph convolution networks contrastive learning |
| title | Efficient Graph Collaborative Filtering via Contrastive Learning |
| title_full | Efficient Graph Collaborative Filtering via Contrastive Learning |
| title_fullStr | Efficient Graph Collaborative Filtering via Contrastive Learning |
| title_full_unstemmed | Efficient Graph Collaborative Filtering via Contrastive Learning |
| title_short | Efficient Graph Collaborative Filtering via Contrastive Learning |
| title_sort | efficient graph collaborative filtering via contrastive learning |
| topic | recommender systems efficient recommendation collaborative filtering graph convolution networks contrastive learning |
| url | https://www.mdpi.com/1424-8220/21/14/4666 |
| work_keys_str_mv | AT zhiqiangpan efficientgraphcollaborativefilteringviacontrastivelearning AT honghuichen efficientgraphcollaborativefilteringviacontrastivelearning |