Sommelier: Curating DNN Models for the Masses
Summary: Sommelier is an indexing/query engine for DNN model repos that selects models to meet accuracy and budget targets. It fuses semantic correlation with a resource index to pick candidates, achieving target accuracy and cutting tail latency up to 6x. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Peizhen Guo
- 2. Bo Hu
- 3. Wenjun Hu
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,479 | Alsatian: Optimizing Model Search for Deep Transfer Learning | 2025 | SIGMOD | 4.1905499e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 943 | A Formal Approach to Finding Explanations for Database Queries | 2014 | SIGMOD | 0.00015140995 |
| 1,024 | DBSherlock: A Performance Diagnostic Tool for Transactional Databases | 2016 | SIGMOD | 0.00014601525 |
| 2,158 | DIFF: A Relational Interface for Large-Scale Data Explanation | 2019 | VLDB | 9.4117885e-05 |
| 3,333 | A Demonstration of Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference | 2020 | VLDB | 7.2064333e-05 |
| 4,690 | Multi-Structural Databases | 2005 | PODS | 5.9898251e-05 |
Previous
Page 1 / 1
Next