Scaling deep retrieval with TensorFlow Recommenders and Vertex AI Matching Engine. The goal of this blog is to demonstrate how to implement these deep retrieval techniques using Vertex. In this blog, we will cover the evolution of retrieval modeling and why two-tower encoders are popular for deep retrieval tasks.
Table of contents
BackgroundTwo-towers for deep retrievalDecoupled inference for optimal servingProblem FramingImplementing deep retrieval with TFRSDense and cross layersFeature engineeringEfficient retrieval with Matching EngineConclusionSort: