IRJun 20, 2020

Embedding-based Retrieval in Facebook Search

arXiv:2006.11632v2394 citations
Originality Synthesis-oriented
AI Analysis

This work addresses personalized search in social networks like Facebook, offering incremental improvements by adapting existing EBR techniques to a specific domain.

The paper tackled the challenge of improving Facebook Search by incorporating the user's social graph and context, moving from a Boolean matching model to embedding-based retrieval (EBR), resulting in significant metrics gains in online A/B experiments.

Search in social networks such as Facebook poses different challenges than in classical web search: besides the query text, it is important to take into account the searcher's context to provide relevant results. Their social graph is an integral part of this context and is a unique aspect of Facebook search. While embedding-based retrieval (EBR) has been applied in eb search engines for years, Facebook search was still mainly based on a Boolean matching model. In this paper, we discuss the techniques for applying EBR to a Facebook Search system. We 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. We discuss various tricks and experiences on end-to-end optimization of the whole system, including ANN parameter tuning and full-stack optimization. Finally, we present our progress on two selected advanced topics about modeling. We evaluated EBR on verticals for Facebook Search with significant metrics gains observed in online A/B experiments. We believe this paper will provide useful insights and experiences to help people on developing embedding-based retrieval systems in search engines.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes