Heterogeneous Graph Neural Architecture Search with GPT-4
This work addresses a domain-specific problem for researchers and practitioners in graph neural networks, offering an incremental improvement over existing HGNAS algorithms.
The paper tackles the problem of inefficient and unstable heterogeneous graph neural architecture search (HGNAS) by introducing a GPT-4 based model, GHGNAS, which improves search efficiency and accuracy, as shown by experimental results indicating it runs more effectively and stably than previous methods.
Heterogeneous graph neural architecture search (HGNAS) represents a powerful tool for automatically designing effective heterogeneous graph neural networks. However, existing HGNAS algorithms suffer from inefficient searches and unstable results. In this paper, we present a new GPT-4 based HGNAS model to improve the search efficiency and search accuracy of HGNAS. Specifically, we present a new GPT-4 enhanced Heterogeneous Graph Neural Architecture Search (GHGNAS for short). The basic idea of GHGNAS is to design a set of prompts that can guide GPT-4 toward the task of generating new heterogeneous graph neural architectures. By iteratively asking GPT-4 with the prompts, GHGNAS continually validates the accuracy of the generated HGNNs and uses the feedback to further optimize the prompts. Experimental results show that GHGNAS can design new HGNNs by leveraging the powerful generalization capability of GPT-4. Moreover, GHGNAS runs more effectively and stably than previous HGNAS models based on reinforcement learning and differentiable search algorithms.