Graph Neural Architecture Search with GPT-4

arXiv:2310.01436v2 Announce Type: replace
Abstract: Graph Neural Architecture Search (GNAS) has shown promising results in automatically designing graph neural networks. However, GNAS still requires intensive human labor with rich domain knowledge to design the search space and search strategy. In this paper, we integrate GPT-4 into GNAS and propose a new GPT-4 based Graph Neural Architecture Search method (GPT4GNAS for short). The basic idea of our method is to design a new class of prompts for GPT-4 to guide GPT-4 …

abstract architecture arxiv cs.ai cs.lg design designing domain domain knowledge gpt gpt-4 graph graph neural networks however human knowledge labor networks neural architecture search neural networks paper results search space strategy type