DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation
Summary: Targets declarative top-K “interpretation-by-example” queries over DNN activations via a compact indexing scheme and optimized execution. Instance-optimal algorithm + <20% materialization cost yields up to 63x single-query speedups and consistent multi-query dominance. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Dong He (University of Washington)
- 2. Maureen Daum (University of Washington)
- 3. Walter Cai (University of Washington)
- 4. Magdalena Balazinska (University of Washington)
BibTeX Citation
@article{he_vldb22,
title = {{DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation}},
author = {He, Dong and Daum, Maureen and Cai, Walter and Balazinska, Magdalena},
journal = {PVLDB},
series = {{VLDB} '22},
volume = {15},
number = {1},
pages = {98--111},
doi = {10.14778/3485450.3485460},
url = {https://doi.org/10.14778/3485450.3485460},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,447 | EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions | 2023 | VLDB | 5.5240718e-05 |
| 9,645 | Self-Enhancing Video Data Management System for Compositional Events with Large Language Models | 2025 | SIGMOD | 5.1453267e-05 |
| 11,556 | MetaStore: Analyzing Deep Learning Meta-Data at Scale | 2024 | VLDB | 4.9793485e-05 |
| 11,624 | Demonstration of MaskSearch: Efficiently Querying Image Masks for Machine Learning Workflows | 2024 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2 | R-Trees: A Dynamic Index Structure For Spatial Searching | 1984 | SIGMOD | 0.001992968 |
| 5 | Optimal Aggregation Algorithms for Middleware [Extended Abstract] | 2001 | PODS | 0.0010679641 |
| 1,502 | VisTrails: Visualization meets Data Management | 2006 | SIGMOD | 0.00010456416 |
| 1,535 | Top-k Query Evaluation with Probabilistic Guarantees | 2004 | VLDB | 0.00010331242 |
| 1,568 | HELIX: Holistic Optimization for Accelerating Iterative Machine Learning | 2019 | VLDB | 0.0001021302 |
| 1,691 | MISTIQUE: A System to Store and Query Model Intermediates for Model Diagnosis | 2018 | SIGMOD | 9.8570722e-05 |
| 2,006 | IO-Top-k: Index-access Optimized Top-k Query Processing | 2006 | VLDB | 9.199795e-05 |
| 3,049 | Joining Ranked Inputs in Practice | 2002 | VLDB | 7.7090549e-05 |
| 3,656 | Best Position Algorithms for Top-k Queries | 2007 | VLDB | 7.1256193e-05 |
| 6,559 | DeepBase: Deep Inspection of Neural Networks | 2019 | SIGMOD | 5.7489089e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,844 | Serving Deep Learning Models with Deduplication from Relational Databases | 2022 | VLDB |
| 2 | 11,857 | DeepO: A Learned Query Optimizer | 2022 | SIGMOD |
| 3 | 5,158 | Facilitating SQL Query Composition and Analysis | 2020 | SIGMOD |
| 4 | 4,781 | Learned Approximate Query Processing: Make it Light, Accurate and Fast | 2021 | CIDR |
| 5 | 3,060 | Towards a Hands-Free Query Optimizer through Deep Learning | 2019 | CIDR |
| 6 | 13,746 | Using Deep Learning Models to Replace Large Materialized Views in Relational Database | 2021 | CIDR |
| 7 | 560 | Plan-Structured Deep Neural Network Models for Query Performance Prediction | 2019 | VLDB |
| 8 | 5,804 | Top-K Deep Video Analytics: A Probabilistic Approach | 2021 | SIGMOD |
| 9 | 9,333 | Deep Query Optimization | 2019 | SIGMOD |
| 10 | 10,109 | Everest: A Top-K Deep Video Analytics System | 2022 | SIGMOD |