Towards Versatile Graph Learning Approach: from the Perspective of Large Language Models

arXiv:2402.11641v1 Announce Type: new
Abstract: Graph-structured data are the commonly used and have wide application scenarios in the real world. For these diverse applications, the vast variety of learning tasks, graph domains, and complex graph learning procedures present challenges for human experts when designing versatile graph learning approaches. Facing these challenges, large language models (LLMs) offer a potential solution due to the extensive knowledge and the human-like intelligence. This paper proposes a novel conceptual prototype for designing versatile graph learning …

abstract application applications arxiv challenges cs.lg data designing diverse diverse applications domains experts graph graph learning human language language models large language large language models perspective structured data tasks type vast world