DeepBase: Deep Inspection of Neural Networks
Summary: DeepBase is a declarative system to inspect neural networks via hypothesis-driven annotations and statistical dependencies between units and labels. It unifies analyses and optimizations that speed up Python baselines, enabling reproducible NLP studies. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Thibault Sellam (Columbia University)
- 2. Kevin Lin (Columbia University)
- 3. Ian Huang (Columbia University)
- 4. Michelle Yang (University of California Berkeley)
- 5. Carl Vondrick (Columbia University)
- 6. Eugene Wu (Columbia University)
BibTeX Citation
@inproceedings{sellam_sigmod19,
title = {{DeepBase: Deep Inspection of Neural Networks}},
author = {Sellam, Thibault and Lin, Kevin and Huang, Ian and Yang, Michelle and Vondrick, Carl and Wu, Eugene},
series = {{SIGMOD} '19},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3299869.3300073},
url = {https://dl.acm.org/doi/10.1145/3299869.3300073},
year = {2019}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,584 | Complaint-driven Training Data Debugging for Query 2.0 | 2020 | SIGMOD | 8.3783546e-05 |
| 6,960 | DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation | 2022 | VLDB | 5.7303405e-05 |
| 8,328 | Deep Learning: Systems and Responsibility | 2021 | SIGMOD | 5.4535681e-05 |
| 11,305 | Demonstration of MaskSearch: Efficiently Querying Image Masks for Machine Learning Workflows | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 106 | The MADlib Analytics Library or MAD Skills, the SQL | 2012 | VLDB | 0.00033539462 |
| 408 | MauveDB: Supporting Model-based User Views in Database Systems | 2006 | SIGMOD | 0.00019008806 |
| 518 | Towards a Unified Architecture for in-RDBMS Analytics | 2012 | SIGMOD | 0.00017167492 |
| 1,079 | Hybrid Parallelization Strategies for Large-Scale Machine Learning in SystemML | 2014 | VLDB | 0.00012258469 |
| 1,250 | Data Management in Machine Learning: Challenges, Techniques, and Systems | 2017 | SIGMOD | 0.00011485301 |
| 1,670 | MISTIQUE: A System to Store and Query Model Intermediates for Model Diagnosis | 2018 | SIGMOD | 0.00010045615 |
| 4,214 | The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Velox | 2015 | CIDR | 6.8276099e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 6,960 | DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation | 2022 | VLDB |
| 2 | 10,557 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB |
| 3 | 8,854 | Towards Foundation Database Models | 2025 | CIDR |
| 4 | 2,079 | DBPal: A Fully Pluggable NL2SQL Training Pipeline | 2020 | SIGMOD |
| 5 | 579 | Incremental Knowledge Base Construction Using DeepDive | 2015 | VLDB |
| 6 | 7,684 | Deep Lake: a Lakehouse for Deep Learning | 2023 | CIDR |
| 7 | 8,328 | Deep Learning: Systems and Responsibility | 2021 | SIGMOD |
| 8 | 6,870 | Natural Language Interfaces for Databases with Deep Learning | 2023 | VLDB |
| 9 | 2,175 | From Natural Language Processing to Neural Databases | 2021 | VLDB |
| 10 | 3,339 | A Deep Dive into Deep Learning Approaches for Text-to-SQL Systems | 2021 | SIGMOD |