Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910496837337088 |
|---|---|
| author | Wu, Yihong Zhang, Le Mo, Fengran Zhu, Tianyu Ma, Weizhi Nie, Jian-Yun |
| author_facet | Wu, Yihong Zhang, Le Mo, Fengran Zhu, Tianyu Ma, Weizhi Nie, Jian-Yun |
| contents | Graph-based models and contrastive learning have emerged as prominent methods in Collaborative Filtering (CF). While many existing models in CF incorporate these methods in their design, there seems to be a limited depth of analysis regarding the foundational principles behind them. This paper bridges graph convolution, a pivotal element of graph-based models, with contrastive learning through a theoretical framework. By examining the learning dynamics and equilibrium of the contrastive loss, we offer a fresh lens to understand contrastive learning via graph theory, emphasizing its capability to capture high-order connectivity. Building on this analysis, we further show that the graph convolutional layers often used in graph-based models are not essential for high-order connectivity modeling and might contribute to the risk of oversmoothing. Stemming from our findings, we introduce Simple Contrastive Collaborative Filtering (SCCF), a simple and effective algorithm based on a naive embedding model and a modified contrastive loss. The efficacy of the algorithm is demonstrated through extensive experiments across four public datasets. The experiment code is available at \url{https://github.com/wu1hong/SCCF}. \end{abstract} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13996 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering Wu, Yihong Zhang, Le Mo, Fengran Zhu, Tianyu Ma, Weizhi Nie, Jian-Yun Information Retrieval Graph-based models and contrastive learning have emerged as prominent methods in Collaborative Filtering (CF). While many existing models in CF incorporate these methods in their design, there seems to be a limited depth of analysis regarding the foundational principles behind them. This paper bridges graph convolution, a pivotal element of graph-based models, with contrastive learning through a theoretical framework. By examining the learning dynamics and equilibrium of the contrastive loss, we offer a fresh lens to understand contrastive learning via graph theory, emphasizing its capability to capture high-order connectivity. Building on this analysis, we further show that the graph convolutional layers often used in graph-based models are not essential for high-order connectivity modeling and might contribute to the risk of oversmoothing. Stemming from our findings, we introduce Simple Contrastive Collaborative Filtering (SCCF), a simple and effective algorithm based on a naive embedding model and a modified contrastive loss. The efficacy of the algorithm is demonstrated through extensive experiments across four public datasets. The experiment code is available at \url{https://github.com/wu1hong/SCCF}. \end{abstract} |
| title | Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2406.13996 |