Powering In-Database Dynamic Model Slicing for Structured Data Analytics

TL;DR

This paper presents LEADS, a SQL-aware dynamic model slicing technique that enables efficient, in-database deep learning model customization for structured data analytics, significantly reducing inference latency.

Contribution

LEADS introduces a novel SQL-aware mixture of experts approach for in-database model slicing, improving efficiency and effectiveness in structured data analytics.

Findings

LEADS outperforms baseline models on real-world datasets.

In-database inference with LEADS reduces latency significantly.

The approach scales with complex SQL queries and large datasets.

Abstract

Relational database management systems (RDBMS) are widely used for the storage of structured data. To derive insights beyond statistical aggregation, we typically have to extract specific subdatasets from the database using conventional database operations, and then apply deep neural networks (DNN) training and inference on these subdatasets in a separate analytics system. The process can be prohibitively expensive, especially when there are various subdatasets extracted for different analytical purposes. This calls for efficient in-database support of advanced analytical methods. In this paper, we introduce LEADS, a novel SQL-aware dynamic model slicing technique to customize models for specified SQL queries. LEADS improves the predictive modeling of structured data via the mixture of experts (MoE) and maintains efficiency by a SQL-aware gating network. At the core of LEADS is the construction of a general model with multiple expert sub-models trained over the database. The MoE scales up the modeling capacity, enhances effectiveness, and preserves efficiency by activating necessary experts via the SQL-aware gating network during inference. To support in-database analytics, we build an inference extension that integrates LEADS onto PostgreSQL. Our extensive experiments on real-world datasets demonstrate that LEADS consistently outperforms the baseline models, and the in-database inference extension delivers a considerable reduction in inference latency compared to traditional solutions.