Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916909188907008 |
|---|---|
| author | Cao, Mengyang Yang, Frank F. Jin, Yi Yan, Yijun |
| author_facet | Cao, Mengyang Yang, Frank F. Jin, Yi Yan, Yijun |
| contents | Identifying relevant information among massive volumes of data is a challenge for modern recommendation systems. Graph Neural Networks (GNNs) have demonstrated significant potential by utilizing structural and semantic relationships through graph-based learning. This study assessed the abilities of four GNN architectures, LightGCN, GraphSAGE, GAT, and PinSAGE, on the Amazon Product Co-purchase Network under link prediction settings. We examined practical trade-offs between architectures, model performance, scalability, training complexity and generalization. The outcomes demonstrated each model's performance characteristics for deploying GNN in real-world recommendation scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14059 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph Cao, Mengyang Yang, Frank F. Jin, Yi Yan, Yijun Information Retrieval Machine Learning Identifying relevant information among massive volumes of data is a challenge for modern recommendation systems. Graph Neural Networks (GNNs) have demonstrated significant potential by utilizing structural and semantic relationships through graph-based learning. This study assessed the abilities of four GNN architectures, LightGCN, GraphSAGE, GAT, and PinSAGE, on the Amazon Product Co-purchase Network under link prediction settings. We examined practical trade-offs between architectures, model performance, scalability, training complexity and generalization. The outcomes demonstrated each model's performance characteristics for deploying GNN in real-world recommendation scenarios. |
| title | Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2508.14059 |