VALSE 论文速览 第188期：具有泛化原型的域偏移联邦图学习

论文题目：

Federated Graph Learning under Domain Shift with Generalizable Prototypes

作者列表：

万冠呈 (武汉大学)、黄文柯 (武汉大学)、叶茫 (武汉大学)

B站观看网址：

https://www.bilibili.com/video/BV1UM4m127uT/

论文摘要：

Federated Graph Learning is a privacy-preserving collaborative approach for training a shared model on graph-structured data in the distributed environment. However, in real-world scenarios, the client graph data usually originate from diverse domains, this unavoidably hinders the generalization performance of the final global model. To address this challenge, we start the first attempt to investigate this scenario by learning a well-generalizable model. In order to improve the performance of the global model from different perspectives, we propose a novel framework from both classification model and feature extractor perspectives. Experimental results on various datasets are presented to validate the generalization of the proposed method.

参考文献：

[1] Guancheng Wan, Wenke Huang, Mang Ye, “Federated Graph Learning under Domain Shift with Generalizable Prototypes” in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI, 2024), VANCOUVER, CANADA, 2024.

论文链接：

[https://ojs.aaai.org/index.php/AAAI/article/view/29468]

代码链接：

[https://github.com/GuanchengWan/FGGP]

视频讲者简介：

Guancheng Wan is a student pursuing the bachelor degree at School of Computer Science,Wuhan University. His research interests include graph mining and federated learning.

个人主页：

https://guanchengwan.github.io/

特别鸣谢本次论文速览主要组织者：

月度轮值AC：陈使明 (卡耐基梅隆大学)