IntentGC:a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation
这是阿里巴巴发表在KDD2019的论文,主要是融合了异构信息网络中的许多辅助信息进行推荐。 【原文链接】 【摘要】从常见的用户行为和项目信息中收集了大量的关系，并提出了一个新的框架IntentGC，在图卷积网络上利用显式偏好和异构关系，并减少了不必要的特征交互。 【原理】 1.捕获了大量的异构关系来提高推荐的性能。 2.为了方便操作和提高鲁棒性，将一阶近似的辅助关系转化为二阶近似的更鲁棒性的加权关
相关文章
- 1. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 2. Graph Neural Networks for Social Recommendation
- 3. metapath2vec: Scalable Representation Learning for Heterogeneous Networks
- 4. 意图推荐 Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 5. 【PaperReading】GraphIE：A Graph-Based Framework for Information Extraction
- 6. Controllable Multi-Interest Framework for Recommendation
- 7. 【论文解读 KDD 2019 | MEIRec】Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 8. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation 个人总结
- 9. RKGE Recurrent Knowledge Graph Embedding for Effective Recommendation 论文
- 10. 论文笔记：LightGCN Simplifying and Powering Graph Convolution Network for Recommendation
- 更多相关文章...
- • Swift for 循环 - Swift 教程
- • Scala for循环 - Scala教程
- • Composer 安装与使用
- • PHP开发工具
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. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 2. Graph Neural Networks for Social Recommendation
- 3. metapath2vec: Scalable Representation Learning for Heterogeneous Networks
- 4. 意图推荐 Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 5. 【PaperReading】GraphIE：A Graph-Based Framework for Information Extraction
- 6. Controllable Multi-Interest Framework for Recommendation
- 7. 【论文解读 KDD 2019 | MEIRec】Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 8. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation 个人总结
- 9. RKGE Recurrent Knowledge Graph Embedding for Effective Recommendation 论文
- 10. 论文笔记：LightGCN Simplifying and Powering Graph Convolution Network for Recommendation