DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation
This work addresses the challenge of speeding up interpretation queries for deep neural networks, which is an incremental improvement in a domain-specific area.
The paper tackles the problem of efficiently executing declarative top-k queries for interpreting deep neural networks, resulting in a system that accelerates individual queries by up to 63x while using less than 20% of the storage of full materialization.
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.