SEFRQO combines LLMs, fine-tuning & RAG to tackle the cold-start and generalization across workloads and DBMSes issues.

LIMAO is a lifelong learning framework that can be integrated with many learned query optimizers to boost their adaptability under shifting data/workloads. It supports modular plan decomposition, component reuse, and continual learning without retraining from scratch.

We employ a hybrid quantum-classical approach to generate optimized join order hints that can achieve up to 13x query execution speedup compared to vanilla PostgreSQL.

In this work, we are the first to use conformal prediction to verify, with formal guarantees, the learned query optimizer decisions and avoid disastrous plans. Also, we show how conformal prediction can proactively guide the query plan construction process to obtain verified learned plans upfront.

Q-Data 2025 is organized by @ibrahimsabek.bsky.social and Immanuel Trummer. Should you have any questions, don't hesitate to reach out to them! (3/3)

Check out the topics of interest and the CfP at (qdataworkshop.com). We are allowing submissions for full, short, and abstract papers. The submission deadline is April 20, 2025, and acceptance notifications will be out on May 4, 2025. (2/3)