datafun蒋卓人.pdf

《datafun蒋卓人.pdf》由会员分享，可在线阅读，更多相关《datafun蒋卓人.pdf（52页珍藏版）》请在三个皮匠报告上搜索。

1、DataFunSummit#2024利用大语言模型促进综合图学习能力浙江大学 蒋卓人 蒋卓人浙江大学 公共管理学院 信息资源管理系“百人计划”研究员，博士生导师01为什么应用大语言模型进行图学习02大语言模型进行图学习的现状概述03大语言模型促进跨领域跨任务的统一图学习04潜在研究方向目录DataFunSummit#202401为什么应用大语言模型进行图学习为什么应用大语言模型进行图学习大语言模型的能力图数据的特征为什么应用大语言模型进行图学习大语言模型的能力 LLMs have demonstrated their strong text encoding/decoding ability.

2、Zhao W X,Zhou K,Li J,et al.A survey of large language modelsJ.arXiv preprint arXiv:2303.18223,2023.为什么应用大语言模型进行图学习大语言模型的能力 LLMs have shown newly found emergent ability(e.g.,reasoning).Wei J,Wang X,Schuurmans D,et al.Chain-of-thought prompting elicits reasoning in large language modelsJ.Advances in n

3、eural information processing systems,2022,35:24824-24837.为什么应用大语言模型进行图学习图数据的特征In real world,text and graph usually appears simultaneously.Text data are associated with rich structure information in the form of graphs.Graph data are captioned with rich textual information.DataFunSummit#202402大语言模型进行图

4、学习的现状概述大语言模型进行图学习的现状概述不同的图数据应用场景图任务中大语言模型的不同角色不同的图数据应用场景Jin B,Liu G,Han C,et al.Large language models on graphs:A comprehensive surveyJ.arXivpreprint arXiv:2312.02783,2023.大语言模型进行图学习的现状概述大语言模型进行图学习的现状概述不同的图数据应用场景：Pure GraphWang H,Feng S,He T,et al.Can language models solve graph problems in natural

5、language?J.Advances in Neural Information Processing Systems,2024,36.Definition:Graph with no text information or no semantically rich text information.eg.traffic graphs or power transmission graph.Problems on Pure Graphs:graph reasoning tasks like connectivityshortest pathsubgraph matchinglogical r

6、ule induction大语言模型进行图学习的现状概述Wang H,Feng S,He T,et al.Can language models solve graph problems in natural language?J.Advances in Neural Information Processing Systems,2024,36.不同的图数据应用场景：Pure GraphGraph with no text information or no semantically rich text information.eg.traffic graphs or power transm