ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs

arXiv:2402.11235v1 Announce Type: new
Abstract: With the development of foundation models such as large language models, zero-shot transfer learning has become increasingly significant. This is highlighted by the generative capabilities of NLP models like GPT-4, and the retrieval-based approaches of CV models like CLIP, both of which effectively bridge the gap between seen and unseen data. In the realm of graph learning, the continuous emergence of new graphs and the challenges of human labeling also amplify the necessity for zero-shot …

abstract arxiv become bridge capabilities clip cs.lg dataset development foundation gap generative gpt gpt-4 graphs language language models large language large language models nlp nlp models retrieval transfer transfer learning type zero-shot