HKUDS/GraphEdit
"GraphEdit: Large Language Models for Graph Structure Learning"
This project helps researchers and data scientists working with academic citation networks like Pubmed, Citeseer, and Cora to improve the accuracy of their graph-based analyses. It takes raw text data and existing graph structures, uses large language models to refine the connections between entities, and outputs an optimized graph ready for more accurate predictive modeling or classification. This is designed for those who need to extract better insights from complex, interconnected data.
143 stars. No commits in the last 6 months.
Use this if you are performing tasks like document classification or link prediction on academic citation datasets and want to leverage large language models to enhance the underlying graph structure for better performance.
Not ideal if your data is not structured as a graph or if you are not working within research domains focused on citation network analysis.
Stars
143
Forks
15
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HKUDS/GraphEdit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RManLuo/reasoning-on-graphs
Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable...
alibaba/GraphTranslator
GraphTranslator:Aligning Graph Model to Large Language Model for Open-ended Tasks
HKUDS/OpenGraph
[EMNLP'2024] "OpenGraph: Towards Open Graph Foundation Models"
iMoonLab/LLM4Hypergraph
The source code of ICLR 2025 "Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?"
UCSC-REAL/DS2
[ICLR 2025] Official implementation of paper "Improving Data Efficiency via Curating LLM-Driven...