HGCL: Hierarchical Graph Contrastive Learning for User-Item Recommendation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913857912438784 |
|---|---|
| author | Xue, Jiawei Yang, Zhen Lin, Haitao Zhang, Ziji Wang, Luzhu Gu, Yikun Xu, Yao Li, Xin |
| author_facet | Xue, Jiawei Yang, Zhen Lin, Haitao Zhang, Ziji Wang, Luzhu Gu, Yikun Xu, Yao Li, Xin |
| contents | Graph Contrastive Learning (GCL), which fuses graph neural networks with contrastive learning, has evolved as a pivotal tool in user-item recommendations. While promising, existing GCL methods often lack explicit modeling of hierarchical item structures, which represent item similarities across varying resolutions. Such hierarchical item structures are ubiquitous in various items (e.g., online products and local businesses), and reflect their inherent organizational properties that serve as critical signals for enhancing recommendation accuracy. In this paper, we propose Hierarchical Graph Contrastive Learning (HGCL), a novel GCL method that incorporates hierarchical item structures for user-item recommendations. First, HGCL pre-trains a GCL module using cross-layer contrastive learning to obtain user and item representations. Second, HGCL employs a representation compression and clustering method to construct a two-hierarchy user-item bipartite graph. Ultimately, HGCL fine-tunes user and item representations by learning on the hierarchical graph, and then provides recommendations based on user-item interaction scores. Experiments on three widely adopted benchmark datasets ranging from 70K to 382K nodes confirm the superior performance of HGCL over existing baseline models, highlighting the contribution of hierarchical item structures in enhancing GCL methods for recommendation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19020 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HGCL: Hierarchical Graph Contrastive Learning for User-Item Recommendation Xue, Jiawei Yang, Zhen Lin, Haitao Zhang, Ziji Wang, Luzhu Gu, Yikun Xu, Yao Li, Xin Information Retrieval Artificial Intelligence Graph Contrastive Learning (GCL), which fuses graph neural networks with contrastive learning, has evolved as a pivotal tool in user-item recommendations. While promising, existing GCL methods often lack explicit modeling of hierarchical item structures, which represent item similarities across varying resolutions. Such hierarchical item structures are ubiquitous in various items (e.g., online products and local businesses), and reflect their inherent organizational properties that serve as critical signals for enhancing recommendation accuracy. In this paper, we propose Hierarchical Graph Contrastive Learning (HGCL), a novel GCL method that incorporates hierarchical item structures for user-item recommendations. First, HGCL pre-trains a GCL module using cross-layer contrastive learning to obtain user and item representations. Second, HGCL employs a representation compression and clustering method to construct a two-hierarchy user-item bipartite graph. Ultimately, HGCL fine-tunes user and item representations by learning on the hierarchical graph, and then provides recommendations based on user-item interaction scores. Experiments on three widely adopted benchmark datasets ranging from 70K to 382K nodes confirm the superior performance of HGCL over existing baseline models, highlighting the contribution of hierarchical item structures in enhancing GCL methods for recommendation tasks. |
| title | HGCL: Hierarchical Graph Contrastive Learning for User-Item Recommendation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2505.19020 |