2 papers
cs.LG2025
UniGTE: Unified Graph-Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains
Duo Wang, Yuan Zuo, Guangyue Lu +1
Generalizing to unseen graph tasks without task-specific supervision is challenging: conventional graph neural networks are typically tied to a fixed label space, while large langu…
cs.LG2025
Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning
Yicong Wu, Guangyue Lu, Yuan Zuo +2
Generalizing to unseen graph tasks without task-pecific supervision remains challenging. Graph Neural Networks (GNNs) are limited by fixed label spaces, while Large Language Models…