DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation
arXiv:2104.02234
Abstract
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.
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"
References in corpus (5)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Understanding Neural Networks Through Deep Visualization
- Object Detectors Emerge in Deep Scene CNNs
- Understanding the Role of Individual Units in a Deep Neural Network
- DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation