LLM4GNAS: A Large Language Model Based Toolkit for Graph Neural Architecture Search
This work addresses the problem of reducing manual effort and domain-specific knowledge for researchers and practitioners in graph learning, though it appears incremental as it builds on existing GNAS methods with LLM enhancements.
The paper tackles the challenge of manual adaptation in Graph Neural Architecture Search (GNAS) by introducing LLM4GNAS, a toolkit that uses Large Language Models to automate the process, and reports that it outperforms existing GNAS methods on homogeneous and heterogeneous graph tasks.
Graph Neural Architecture Search (GNAS) facilitates the automatic design of Graph Neural Networks (GNNs) tailored to specific downstream graph learning tasks. However, existing GNAS approaches often require manual adaptation to new graph search spaces, necessitating substantial code optimization and domain-specific knowledge. To address this challenge, we present LLM4GNAS, a toolkit for GNAS that leverages the generative capabilities of Large Language Models (LLMs). LLM4GNAS includes an algorithm library for graph neural architecture search algorithms based on LLMs, enabling the adaptation of GNAS methods to new search spaces through the modification of LLM prompts. This approach reduces the need for manual intervention in algorithm adaptation and code modification. The LLM4GNAS toolkit is extensible and robust, incorporating LLM-enhanced graph feature engineering, LLM-enhanced graph neural architecture search, and LLM-enhanced hyperparameter optimization. Experimental results indicate that LLM4GNAS outperforms existing GNAS methods on tasks involving both homogeneous and heterogeneous graphs.