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. We prove that the proposed query execution algorithm is instance optimal. Experiments with our prototype show that DeepEverest, using less than 20% of the 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.
@article{arxiv.2104.02234,
title = {DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation},
author = {Dong He and Maureen Daum and Walter Cai and Magdalena Balazinska},
journal= {arXiv preprint arXiv:2104.02234},
year = {2023}
}
Comments
This is an extended technical report for the following paper: "DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation. PVLDB, 15(1): 98 - 111, 2021. doi:10.14778/3485450.3485460"