:: Learning with Knowledge Graphs ::

December - 01 - 2023
Shanghai, China

Shanghai World Trade Mall Co., Ltd.
2299 Yan'an Rd (W), Changning District

Time
17:30-19:50

Panel Discussion

What opportunities can LLMs bring to knowledge graph learning?

Thumbnail Image

Dr. Yao Ma
Rensselaer Polytechnic Institute

Thumbnail Image

Dr. Qiaoyu Tan
New York University Shanghai

Thumbnail Image

Dr. Hao Chen
The Hong Kong Polytechnic University

Accepted Papers

ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs
Yucheng Shi (University of Georgia), Hehuan Ma (University of Texas at Arlington), Wenliang Zhong (University of Texas at Arlington), Qiaoyu Tan (New York University Shanghai), Gengchen Mai (New York University Shanghai), Xiang Li (Massachusetts General Hospital and Harvard Medical School), Tianming Liu (University of Georgia), and Junzhou Huang (University of Texas at Arlington)

KOSA: KO Enhanced Salary Analytics based on Knowledge Graph and LLM Capabilities
Fei Huang, Yi Deng, Chen Zhang, Menghao Guo, Kai Zhan, Zeyi Sun, Jinling Jiang, Shanxin Sun, Xindong Wu (Zhejiang Lab)

CrsKGE-RSAN: Conflict Resolution Strategy for Knowledge Graph Completion
Jie Chen, Xin Zhang, Wuyang Zhang, Siyu Tan, Shu Zhao (Anhui University)

How to Use Language Expert to Assist Inference for Visual Commonsense Reasoning
Zijie Song, Wenbo Hu, Hao Ye, Richang Hong (Hefei University of Technology)

Graph Neural Networks with Non-Recursive Message Passing
Qiaoyu Tan (New York University Shanghai), Xin Zhang (The Hong Kong Polytechnic University), Jiahe Du (The Hong Kong Polytechnic University), Xiao Huang (The Hong Kong Polytechnic University)

Alleviating Behavior Data Imbalance for Multi-Behavior Graph Collaborative Filtering
Yijie Zhang (Jinan University), Yuanchen Bei (Zhejiang University), Shiqi Yang (Jinan University), Hao Chen (The Hong Kong Polytechnic University), Zhiqing Li (South China Agricultural University), Lijia Chen (South China Agricultural University), and Feiran Huang (Jinan University)

About This Workshop

We aim at highlighting the opportunities and challenges in learning with knowledge graphs. Knowledge graphs (KGs) could effectively integrate a large number of real-world assertions, and improve the performance of various applications, such as recommendation, search, and question answering. Many large-scale KGs have been developed, such as Freebase and YAGO. By embedding KGs into low-dimensional vectors, we could integrate KGs into deep learning models and enhance the performance of various prediction tasks. Many recent techniques, such as graph neural networks, contrastive learning, and ChatGPT, have brought opportunities and challenges to learning with knowledge graphs. For example, as a language model, ChatGPT could potentially be used to interpret the semantic meaning of KGs. This workshop aims to engage with active researchers from KG communities, natural language processing communities, data science communities, and other communities, and deliver state-of-the-art research insights into the core challenges in KG learning.

Primary Contact

Xiao Huang, xiaohuang@comp.polyu.edu.hk