ChatGraph: Chat with Your Graphs

Yun Peng, Sen Lin, Qian Chen, Shaowei Wang*, Lyu Xu*, Xiaojun Ren*, Yafei Li, Jianliang Xu

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Graph analysis is fundamental in real-world applications. Traditional approaches rely on SPARQL-like languages or clicking-and-dragging interfaces to interact with graph data. However, these methods either require users to possess high programming skills or support only a limited range of graph analysis functionalities. To address the limitations, we propose a large language model (LLM)-based framework called Chat-Graph. With ChatGraph, users can interact with graphs through natural language, making it easier to use and more flexible than traditional approaches. The core of ChatGraph lies in generating chains of graph analysis APIs based on the understanding of the texts and graphs inputted in the user prompts. To achieve this, ChatGraph consists of three main modules: an API retrieval module that searches for relevant APIs, a graph-aware LLM module that enables the LLM to comprehend graphs, and an API chain-oriented finetuning module that guides the LLM in generating API chains. We have implemented ChatGraph and will showcase its usability and efficiency in four scenarios using real-world graphs.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE 40th International Conference on Data Engineering, ICDE 2024
PublisherIEEE Computer Society
Pages5445-5448
Number of pages4
ISBN (Electronic)9798350317152
DOIs
Publication statusPublished - 13 May 2024
Event40th IEEE International Conference on Data Engineering, ICDE 2024 - Kinepolis Jaarbeurs theater, Utrecht, Netherlands
Duration: 13 May 202417 May 2024
https://icde2024.github.io/papers.html (Link to conference's schedule )
https://icde2024.github.io/index.html (Conference's website)
https://ieeexplore.ieee.org/xpl/conhome/10597630/proceeding (Conference's proceeding)

Publication series

NameProceedings - International Conference on Data Engineering
ISSN (Print)1084-4627
ISSN (Electronic)2375-0286

Conference

Conference40th IEEE International Conference on Data Engineering, ICDE 2024
Country/TerritoryNetherlands
CityUtrecht
Period13/05/2417/05/24
Internet address

Scopus Subject Areas

  • Software
  • Signal Processing
  • Information Systems

User-Defined Keywords

  • API chain generation
  • Graph analysis
  • Large language models

Cite this