Contact

<aside> 🥰 I am Yufei Li, a third-year undergraduate student majoring in Computer Science at Sichuan University (Chengdu, China). Currently, I am in AI-System Lab, under the supervision of Prof. Mingjie Tang.

Previously, I worked with Prof.Yuanhang Zheng on Inteligent Decision.

My research interests are generally in Database, Large Language Models and Data Mining .

My dream is to conduct impactful research aimed at advancing the growth of database&LLM communities, while also create exceptional data-driven projects that could benefit the lives of human beings.

I am a highly motivated and passionate undergraduate seeking admission to a Ph.D. program.

</aside>

<aside> 💡 Recently I am doing exploration on query optimizing under the scenario of Text2Code.

I found that the python library SQLGLOT is great and I am diving into its mechanism.

</aside>

<aside> 🤩 Good News:

“GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization” to PVLDB is accepted!

</aside>

📕 Publications

1. GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization

Jiale Lao, Yibo Wang, Yufei Li, Jianping Wang, Yunjia Zhang, Zhiyuan Chen, Wanghu Chen, Mingjie Tang, Jianguo Wang (The third author)

GPTuner: A Manual-Reading Database Tuning System via GPT-Guided...

Very Large Data Bases Conference (VLDB),2024.

<aside> 💡 What we did…

Designed and implemented GPTuner, a novel manual-reading database tuning system that automatically exploits domain knowledge to enhance the knob tuning process.
Developed a LLM-based data pipeline, a prompt ensemble algorithm, a workload-aware and training-free knob selection strategy, and a Coarse-to-Fine Bayesian Optimization Framework.
Evaluated GPTuner under different benchmarks, metrics and DBMS. It identifies better configurations 16x faster and achieves 30% performance improvement over the best-performing alternative. </aside>

2. A Demonstration of GPTuner: A GPT-Based Manual-Reading Database Tuning System

Jiale Lao, Yibo Wang*, Yufei Li*, Jianping Wang, Yunjia Zhang, Zhiyuan Chen, Wanghu Chen, Mingjie Tang, Jianguo Wang (co-authored)*

GPTuner Demo (SIGMOD'24)

Special Interest Group on Management Of Data (SIGMOD), 2024.

<aside> 💡 What we did…

Engaged users to probe into the ingenious LLM-powered pipeline which refines and unifies heterogeneous knowledge to guide system optimization.
Unleashed the potential of everyday users, enabling them to delve into the nuances of knob features and maximize the efficiency of their tailored DBMS seamlessly.
Empowered DBAs to supercharge GPTuner with their priceless tuning expertise expressed in natural language and witness how it can be customized to the Coarse-to-Fine Optimization Framework.
Outcomes: a demo paper submitted to SIGMOD 2024, and an open-source project with more than 3000 views,200 clones and 50 stars on GitHub. </aside>

3. Intelligent bi-objective optimization method for large-scale group decision-making based on hesitant fuzzy linguistic preference relations with granularity level

Yuanhang Zheng, Zeshui Xu, Yufei Li, Zhang Yi (The third author)

Proceedings of IEEE Transactions on Fuzzy Systems, Under Revision,2024.

<aside> 💡 What we did…

Developed a double objective differential evolution algorithm to find the optimal expert opinion weight.
Design experiments to prove that proposed algorithm performs better than single objective situation and the other two methods proposed before. </aside>