Large language models simplify complex graph rule mining queries
Empowering Users in Graph Rule Mining via Large Language Models
Human-Computer Interaction
Summary
Finding patterns in complex network data usually requires experts who know graph theory and special query languages. The authors show how large language models (LLMs) can help regular users by turning natural language questions about graphs into precise graph mining queries. This approach lets people create, improve, and understand rules about graph data more easily without needing deep technical knowledge.
What this means in practice
- •For data engineers: Create complex graph mining queries in natural language for analyzing connected data without deep graph expertise.
- •For business intelligence teams: Interpret and refine graph association rules in intuitive language to gain insights from relational data structures more easily.
Authors
Francesco Cambria, Francesco Invernici, Andrea Colombo, Anna Bernasconi
Abstract
In the era of interconnected data, graphs have emerged as an effective abstraction for modeling complex systems in an intuitive format, especially with the rise of Property Graphs, which offer an intuitive and scalable way of navigating non-intuitive structures. In this context, graph mining techniques have been developed for testing complex graph-based rules, as the MINE GRAPH RULE operator, which, however, require users to have prior expertise both in graph theory and formal query language. In this work, we propose to bridge the gap between users and the graph-association rule-mining process by showing how Large Language Models (LLMs) can be easily prompted to formulate, refine, and interpret complex relational rules, directly producing MINE GRAPH RULE queries.