IntentGC:a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation
這是阿里巴巴發表在KDD2019的論文,主要是融合了異構信息網絡中的許多輔助信息進行推薦。 【原文鏈接】 【摘要】從常見的用戶行爲和項目信息中收集了大量的關係，並提出了一個新的框架IntentGC，在圖卷積網絡上利用顯式偏好和異構關係，並減少了不必要的特徵交互。 【原理】 1.捕獲了大量的異構關係來提高推薦的性能。 2.爲了方便操作和提高魯棒性，將一階近似的輔助關係轉化爲二階近似的更魯棒性的加權關
相關文章
- 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. 意圖推薦 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. 【論文解讀 KDD 2019 | MEIRec】Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 8. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation 個人總結
- 9. RKGE Recurrent Knowledge Graph Embedding for Effective Recommendation 論文
- 10. 論文筆記：LightGCN Simplifying and Powering Graph Convolution Network for Recommendation
- 更多相關文章...
- • Swift for 循環 - Swift 教程
- • Scala for循環 - Scala教程
- • Composer 安裝與使用
- • PHP開發工具
相關標籤/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。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 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. 意圖推薦 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. 【論文解讀 KDD 2019 | MEIRec】Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
- 8. Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation 個人總結
- 9. RKGE Recurrent Knowledge Graph Embedding for Effective Recommendation 論文
- 10. 論文筆記：LightGCN Simplifying and Powering Graph Convolution Network for Recommendation