Database Native Model Selection: Harnessing Deep Neural Networks in Database Systems
Summary: Introduces TRAILS, an SLO-aware, in-DB model-selection system that combines a new training-free metric (JacFlow) with a two-phase filtering+refinement pipeline to marry training-free efficiency and training-based effectiveness. PostgreSQL-integrated coordinator enables declarative in-DB selection and yields up to 24x speedups and 29x compute savings versus prior systems. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Naili Xing
- 2. Shaofeng Cai
- 3. Gang Chen
- 4. Zhaojing Luo
- 5. Beng Chin Ooi
- 6. Jian Pei
Incoming Citations (Sorted by Pagerank)
Showing 5 of 5 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,688 | NeurDB: On the Design and Implementation of an AI-powered Autonomous Database | 2025 | CIDR | 4.4673127e-05 |
| 9,320 | Powering In-Database Dynamic Model Slicing for Structured Data Analytics | 2024 | VLDB | 4.3556432e-05 |
| 10,095 | NeurStore: Efficient In-database Deep Learning Model Management System | 2026 | SIGMOD | 4.1945683e-05 |
| 10,100 | AixelNet: A Pre-trained Model with Table-aware Adaptation for Structured Data Prediction | 2026 | SIGMOD | 4.1945683e-05 |
| 10,130 | MorphingDB: A Task-Centric AI-Native DBMS for Model Management and Inference | 2026 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 19 of 19 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next