Automated Decision-Making on Networks with LLMs through Knowledge-Guided Evolution

TL;DR

This paper introduces LLMNet, a system that uses Large Language Models and knowledge-guided evolution to automate the configuration and refinement of Graph Neural Networks for various graph learning tasks, demonstrating superior performance across multiple datasets.

Contribution

The paper presents a novel approach combining LLMs with knowledge-guided evolution to automate GNN design, reducing manual effort and improving model performance.

Findings

Outperforms existing methods on twelve datasets

Effective in three different graph learning tasks

Validates the use of knowledge-guided evolution for GNN configuration

Abstract

Effective decision-making on networks often relies on learning from graph-structured data, where Graph Neural Networks (GNNs) play a central role, but they take efforts to configure and tune. In this demo, we propose LLMNet, showing how to design GNN automated through Large Language Models. Our system develops a set of agents that construct graph-related knowlege bases and then leverages Retrieval-Augmented Generation (RAG) to support automated configuration and refinement of GNN models through a knowledge-guided evolution process. These agents, equipped with specialized knowledge bases, extract insights into tasks and graph structures by interacting with the knowledge bases. Empirical results show LLMNet excels in twelve datasets across three graph learning tasks, validating its effectiveness of GNN model designing.