I’m a Second-year Ph.D. student in the School of Data Science at The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), advised by Prof. Yixiang Fang, and have a closely connection with Prof. Chenhao Ma. I got my Master degree from Harbin Institute of Technology Shenzhen in June 2022, under the supervision of Prof. Yunming Ye. Before that, I received my Bachelor’s degree from Harbin Institute of Technology in June 2020.

I am always open for possible collaborations, and visiting opportunities, please do not hesitate to contact me if you are interested!

Interests

My research interests mainly focus on large-scale data management and data mining, particularly graph data management and Large Language Models (LLMs) for data management. Specifically, my research interest lies in the span of the following topics:

• Build efficient and lightweight graph-based retrieval-augmented generation (RAG) methods and systems to enhance the factual accuracy, adaptability, interpretability, and trustworthiness of next-generation language models. For this topic: I am focusing on developing a in-depth study about where are we for GraphRAG !!!!!
• Design simple yet effective algorithms for graph mining, utilizing linear programming and spectral methods, focusing on graph clustering and densest subgraph discovery.
• Inspired by the success of LLMs in the fields of Natural Language Processing (NLP) and Computer Vision (CV), Yingli aims to develop pre-trained models for databases, including graph databases, to enhance the generalization capabilities of intelligent database models. For this topic: I am focusing on designing a pre-trained model for realistic scenario latency prediction!!!
• Develope tools or systems that utilize LLM for data analysis tasks, such as data2insight.

Yingli is working hard 😭😭😭 to produce impactful 🔥 and novel work 🌟, but I often feel confused about (1) how to select a good topic; (2) which topic is more impactful; and (3) how to design a new idea.

News

• 2024.11 💥💥 One Paper “PRICE: A Pretrained Model for Cross-Database Cardinality Estimation” is accepted by VLDB 2025!
• 2024.06 💥💥 One Paper “ Efficient Maximal Motif-Clique Enumeration over Large Heterogeneous Information Networks” is accepted by VLDB 2024!
• 2024.06 💥💥 Our paper about the systemly benchmarck and analysis of densest subgraph discovery is available on arXiv! [arXiv]!
• 2024.04 💥💥 One Paper “Efficient Parallel D-core Decomposition at Scale” is accepted by VLDB 2024!
• 2024.02 💥💥 One Paper “A Counting-based Approach for Efficient 𝑘-Clique Densest Subgraph Discovery” is accepted by SIGMOD 2024!
• 2023.05 💥💥 One Paper “Influential Community Search over Large Heterogeneous Information Networks” is accepted by VLDB 2023!

Selected Publications

• [VLDB2024] Efficient Maximal Motif-Clique Enumeration over Large Heterogeneous Information Networks
  Yingli Zhou, Yixiang Fang, Chenhao Ma, Tianci Hou, Xin Huang

• [VLDB2024] Efficient Parallel D-core Decomposition at Scale
  Wensheng Luo, Yixiang Fang, Chunxu Lin, Yingli Zhou

• [SIGMOD2024] A Counting-based Approach for Efficient 𝑘-Clique Densest Subgraph Discovery
  Yingli Zhou, Qingshuo Guo, Yixiang Fang, Chenhao Ma

• [VLDB2023] Influential Community Search over Large Heterogeneous Information Networks
  Yingli Zhou, Yixiang Fang, Wensheng Luo, Yunming Ye | [pdf] | [Code]

Selected Awards

• Best teaching assistant, CUHK-Shenzhen, 2023
• Outstanding Graduates of Harbin Institute of Technology, 2020
• Outstanding Undergraduate Thesis of Harbin Institute of Technology, 2020