【SR-GNN】Session-based Recommendation with Graph Neural Networks详解
结构图： 首先，将所有会话序列建模为定向会话图，其中每个会话序列可以作为子图处理。然后依次处理每个会话图，通过门控图神经网络得到每个图中所有节点的潜在向量。然后，我们将每个会话表示为全局首选项和用户当前对该会话的兴趣的组合，其中这些全局和本地会话嵌入向量都由节点的潜在向量组成。最后，对于每个会话，我们预测每个条目成为下一个单击的概率。在真实数据集上进行的大量实验证明了该方法的有效性。 开源代码在：
相关文章
- 1. GNN:Session-based Recommendation with Graph Neural Networks简介
- 2. Graph Neural Networks for Social Recommendation
- 3. Memory Augmented Graph Neural Networks for Sequential Recommendation翻译
- 4. Few-shot Learning with Graph Neural Networks
- 5. Few-Shot Learning with Graph Neural Networks
- 6. Overlapping Community Detection with Graph Neural Networks
- 7. Structural Image Classification with Graph Neural Networks
- 8. IMAGE DENOISING WITH GRAPH-CONVOLUTIONAL NEURAL NETWORKS
- 9. Graph-based Dependency Parsing with Graph Neural Networks
- 10. 笔记《Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels》-NeurIPS 2019
- 更多相关文章...
- • 免费ARP详解 - TCP/IP教程
- • *.hbm.xml映射文件详解 - Hibernate教程
- • Flink 数据传输及反压详解
- • 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. GNN:Session-based Recommendation with Graph Neural Networks简介
- 2. Graph Neural Networks for Social Recommendation
- 3. Memory Augmented Graph Neural Networks for Sequential Recommendation翻译
- 4. Few-shot Learning with Graph Neural Networks
- 5. Few-Shot Learning with Graph Neural Networks
- 6. Overlapping Community Detection with Graph Neural Networks
- 7. Structural Image Classification with Graph Neural Networks
- 8. IMAGE DENOISING WITH GRAPH-CONVOLUTIONAL NEURAL NETWORKS
- 9. Graph-based Dependency Parsing with Graph Neural Networks
- 10. 笔记《Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels》-NeurIPS 2019