MixDec Sampling: A Soft Link-based Sampling Method of Graph Neural Network for Recommendation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929711840493568 |
|---|---|
| author | Xie, Xiangjin Chen, Yuxin Wang, Ruipeng Ouyang, Kai Zhang, Zihan Zheng, Hai-Tao Qian, Buyue Zheng, Hansen Hu, Bo Zhuo, Chengxiang Li, Zang |
| author_facet | Xie, Xiangjin Chen, Yuxin Wang, Ruipeng Ouyang, Kai Zhang, Zihan Zheng, Hai-Tao Qian, Buyue Zheng, Hansen Hu, Bo Zhuo, Chengxiang Li, Zang |
| contents | Graph neural networks have been widely used in recent recommender systems, where negative sampling plays an important role. Existing negative sampling methods restrict the relationship between nodes as either hard positive pairs or hard negative pairs. This leads to the loss of structural information, and lacks the mechanism to generate positive pairs for nodes with few neighbors. To overcome limitations, we propose a novel soft link-based sampling method, namely MixDec Sampling, which consists of Mixup Sampling module and Decay Sampling module. The Mixup Sampling augments node features by synthesizing new nodes and soft links, which provides sufficient number of samples for nodes with few neighbors. The Decay Sampling strengthens the digestion of graph structure information by generating soft links for node embedding learning. To the best of our knowledge, we are the first to model sampling relationships between nodes by soft links in GNN-based recommender systems. Extensive experiments demonstrate that the proposed MixDec Sampling can significantly and consistently improve the recommendation performance of several representative GNN-based models on various recommendation benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08161 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MixDec Sampling: A Soft Link-based Sampling Method of Graph Neural Network for Recommendation Xie, Xiangjin Chen, Yuxin Wang, Ruipeng Ouyang, Kai Zhang, Zihan Zheng, Hai-Tao Qian, Buyue Zheng, Hansen Hu, Bo Zhuo, Chengxiang Li, Zang Information Retrieval Artificial Intelligence Graph neural networks have been widely used in recent recommender systems, where negative sampling plays an important role. Existing negative sampling methods restrict the relationship between nodes as either hard positive pairs or hard negative pairs. This leads to the loss of structural information, and lacks the mechanism to generate positive pairs for nodes with few neighbors. To overcome limitations, we propose a novel soft link-based sampling method, namely MixDec Sampling, which consists of Mixup Sampling module and Decay Sampling module. The Mixup Sampling augments node features by synthesizing new nodes and soft links, which provides sufficient number of samples for nodes with few neighbors. The Decay Sampling strengthens the digestion of graph structure information by generating soft links for node embedding learning. To the best of our knowledge, we are the first to model sampling relationships between nodes by soft links in GNN-based recommender systems. Extensive experiments demonstrate that the proposed MixDec Sampling can significantly and consistently improve the recommendation performance of several representative GNN-based models on various recommendation benchmarks. |
| title | MixDec Sampling: A Soft Link-based Sampling Method of Graph Neural Network for Recommendation |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2502.08161 |