LLM and Graphs

Link Prediction on Textual Edge Graphs
In this paper, we present a novel framework - LINK2DOC, designed especially for link prediction on textual-edge graphs.
Chen Ling∗, Zhuofeng Li, Yuntong Hu, Zheng Zhang, Zhongyuan Liu, Shuang Zheng, Jian Pei, Liang Zhao
PDF Cite
TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
In this paper, we introduce Textual-Edge Graphs Datasets and Benchmark (TEG-DB), a comprehensive benchmark for textual-edge graphs including 9 comprehensive TEG datasets, a standardized pipeline and extensive experimental results and analysis.
Zhuofeng Li, Zixing Gou*, Xiangnan Zhang, Zhongyuan Liu, Sirui Li, Yuntong Hu, Chen Ling∗, Zheng Zhang, Liang Zhao
PDF Cite Code Dataset
Map to Optimal: Adapting Graph Out-of-Distribution in Test Time
Haoxiang Zhang*, Zhuofeng Li, Qiannan Zhang, Ziyi Kou, Lianyong Qi, Juncheng Li, Shichao Pei
Cite
Learning from Novel Knowledge: Continual Few-shot Knowledge Graph Completion
In this paper, we propose a novel framework designed to equip the few-shot model with the ability to learn sequentially from novel relations.
Zhuofeng Li, Haoxiang Zhang*, Qiannan Zhang, Ziyi Kou, Shichao Pei
Cite Code Dataset