RA-Embedding-based Retrieval in Facebook Search

1.运用场景

    CTR模型/embedding生成/正负样本选择。

2.创新点

    introduce the unified embedding framework developed to model semantic embeddings for personalized search,and the system to serve embedding-based retrieval in a typical search system based on an inverted index.

3.算法原理

3.1 网络框架

3.2 Embedding-based Retrieval in Facebook Search

    Embedding-based Retrieval in Facebook Search论文

4.算法理解

    依据推荐业务场景，选择对应重要的特征融合生成embedding。