Quad-tier entity fusion contrastive representation learning for knowledge aware recommendation system
Knowledge graph (KG) has recently emerged as a powerful source of auxiliary information in the realm of knowledge-aware recommendation (KGR) systems. However, due to the lack of supervision signals caused by the sparse nature of user-item interactions, existing supervised graph neural network (GNN)...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/175884 |
| _version_ | 1811687291230355456 |
|---|---|
| author | Ong, Kenneth Rongqing Qiu, Wei Khong, Andy Wai Hoong |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Ong, Kenneth Rongqing Qiu, Wei Khong, Andy Wai Hoong |
| author_sort | Ong, Kenneth Rongqing |
| collection | NTU |
| description | Knowledge graph (KG) has recently emerged as a powerful source of auxiliary information in the realm of knowledge-aware recommendation (KGR) systems. However, due to the lack of supervision signals caused by the sparse nature of user-item interactions, existing supervised graph neural network (GNN) models suffer from performance degradation. Moreover, the over-smoothing issue further limits the number of GNN layers or hops required to propagate messages-these models ignore the non-local information concealed deep within the knowledge graph. We propose the Quad-Tier Entity Fusion Contrastive Representation Learning (QTEF-CRL) knowledge-aware framework to achieve learning of deep user preferences from four perspectives: the collaborative, semantic, preference, and structural view. Unlike existing methods, the proposed tri-local and single-global quad-tier architecture exploits the knowledge graph holistically to achieve effective self-supervised representation learning. The newly-introduced preference view constructed from the collaborative knowledge graph (CKG) comprises a preference graph and preference-guided GNN that are specifically designed to capture non-local information explicitly. Experiments conducted on three datasets highlight the efficacy of our proposed model. |
| first_indexed | 2024-10-01T05:13:58Z |
| format | Conference Paper |
| id | ntu-10356/175884 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:13:58Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1758842024-05-10T15:43:32Z Quad-tier entity fusion contrastive representation learning for knowledge aware recommendation system Ong, Kenneth Rongqing Qiu, Wei Khong, Andy Wai Hoong School of Electrical and Electronic Engineering 32nd ACM International Conference on Information and Knowledge Management (CIKM'23) Computer and Information Science Recommender system Knowledge graph Users preferences Contrastive learning Knowledge graph (KG) has recently emerged as a powerful source of auxiliary information in the realm of knowledge-aware recommendation (KGR) systems. However, due to the lack of supervision signals caused by the sparse nature of user-item interactions, existing supervised graph neural network (GNN) models suffer from performance degradation. Moreover, the over-smoothing issue further limits the number of GNN layers or hops required to propagate messages-these models ignore the non-local information concealed deep within the knowledge graph. We propose the Quad-Tier Entity Fusion Contrastive Representation Learning (QTEF-CRL) knowledge-aware framework to achieve learning of deep user preferences from four perspectives: the collaborative, semantic, preference, and structural view. Unlike existing methods, the proposed tri-local and single-global quad-tier architecture exploits the knowledge graph holistically to achieve effective self-supervised representation learning. The newly-introduced preference view constructed from the collaborative knowledge graph (CKG) comprises a preference graph and preference-guided GNN that are specifically designed to capture non-local information explicitly. Experiments conducted on three datasets highlight the efficacy of our proposed model. Published version 2024-05-09T01:04:33Z 2024-05-09T01:04:33Z 2023 Conference Paper Ong, K. R., Qiu, W. & Khong, A. W. H. (2023). Quad-tier entity fusion contrastive representation learning for knowledge aware recommendation system. 32nd ACM International Conference on Information and Knowledge Management (CIKM'23), October 2023, 1949-1959. https://dx.doi.org/10.1145/3583780.3615020 9798400701245 https://hdl.handle.net/10356/175884 10.1145/3583780.3615020 2-s2.0-85178102629 October 2023 1949 1959 en © 2023 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution Internatinal 4.0 License. application/pdf |
| spellingShingle | Computer and Information Science Recommender system Knowledge graph Users preferences Contrastive learning Ong, Kenneth Rongqing Qiu, Wei Khong, Andy Wai Hoong Quad-tier entity fusion contrastive representation learning for knowledge aware recommendation system |
| title | Quad-tier entity fusion contrastive representation learning for knowledge aware recommendation system |
| title_full | Quad-tier entity fusion contrastive representation learning for knowledge aware recommendation system |
| title_fullStr | Quad-tier entity fusion contrastive representation learning for knowledge aware recommendation system |
| title_full_unstemmed | Quad-tier entity fusion contrastive representation learning for knowledge aware recommendation system |
| title_short | Quad-tier entity fusion contrastive representation learning for knowledge aware recommendation system |
| title_sort | quad tier entity fusion contrastive representation learning for knowledge aware recommendation system |
| topic | Computer and Information Science Recommender system Knowledge graph Users preferences Contrastive learning |
| url | https://hdl.handle.net/10356/175884 |
| work_keys_str_mv | AT ongkennethrongqing quadtierentityfusioncontrastiverepresentationlearningforknowledgeawarerecommendationsystem AT qiuwei quadtierentityfusioncontrastiverepresentationlearningforknowledgeawarerecommendationsystem AT khongandywaihoong quadtierentityfusioncontrastiverepresentationlearningforknowledgeawarerecommendationsystem |