DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation

04/06/2021

∙

by   Dong He, et al.

∙

0

∙

share

We design, implement, and evaluate DeepEverest, a system for the efficient execution of interpretation by example queries over the activation values of a deep neural network. DeepEverest consists of an efficient indexing technique and a query execution algorithm with various optimizations. Experiments with our prototype implementation show that DeepEverest, using less than 20 storage of full materialization, significantly accelerates individual queries by up to 63x and consistently outperforms other methods on multi-query workloads that simulate DNN interpretation processes.