UniGraph: Learning a Cross-Domain Graph Foundation Model From Natural Language

arXiv:2402.13630v1 Announce Type: new
Abstract: Foundation models like ChatGPT and GPT-4 have revolutionized artificial intelligence, exhibiting remarkable abilities to generalize across a wide array of tasks and applications beyond their initial training objectives. However, when this concept is applied to graph learning, a stark contrast emerges. Graph learning has predominantly focused on single-graph models, tailored to specific tasks or datasets, lacking the ability to transfer learned knowledge to different domains. This limitation stems from the inherent complexity and diversity of …

abstract applications array artificial artificial intelligence arxiv beyond chatgpt concept contrast cs.lg domain foundation foundation model gpt gpt-4 graph graph learning intelligence language natural natural language tasks training type