arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.20105cs.LGcs.CR
收藏

FedSSP:结合谱知识与个性化偏好的联邦图学习

FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference

Wuhan University(武汉大学);National Engineering Research Center for Multimedia Software(国家多媒体软件工程技术研究中心);Institute of Artificial Intelligence(人工智能研究院);School of Computer Science(计算机学院);Taikang Center for Life and Medical Sciences(泰康生命与医学科学中心)

Zihan Tan, Guancheng Wan, Wenke Huang, Mang Ye

AI总结:

针对跨域pFGL中的结构异质性问题,提出FedSSP框架,通过共享通用谱知识并引入个性化偏好模块,在跨数据集与跨域实验中验证了优越性。

摘要:

个性化联邦图学习(pFGL)在不损害隐私的前提下促进了图神经网络(GNN)的去中心化训练,同时能够适应非IID参与方的个性化需求。在跨域场景中,结构异质性给pFGL带来了重大挑战。然而,以往的pFGL方法错误地在全局共享非通用知识,并且在域结构偏移下无法在本地定制个性化解决方案。我们创新性地揭示,图的谱特性能够很好地反映固有的域结构偏移。相应地,我们的方法通过共享通用谱知识来克服这一问题。此外,我们指出了面向图结构的有偏消息传递机制,并提出了个性化偏好模块。结合这两种策略,我们提出了pFGL框架FedSSP,该框架在共享通用Spectral(谱)知识的同时满足图Preferences(偏好)。此外,我们在跨数据集和跨域设置下进行了大量实验,以证明该框架的优越性。代码可在https://github.com/OakleyTan/FedSSP获取。

英文摘要:

Personalized Federated Graph Learning (pFGL) facilitates the decentralized training of Graph Neural Networks (GNNs) without compromising privacy while accommodating personalized requirements for non-IID participants. In cross-domain scenarios, structural heterogeneity poses significant challenges for pFGL. Nevertheless, previous pFGL methods incorrectly share non-generic knowledge globally and fail to tailor personalized solutions locally under domain structural shift. We innovatively reveal that the spectral nature of graphs can well reflect inherent domain structural shifts. Correspondingly, our method overcomes it by sharing generic spectral knowledge. Moreover, we indicate the biased message-passing schemes for graph structures and propose the personalized preference module. Combining both strategies, we propose our pFGL framework FedSSP which Shares generic Spectral knowledge while satisfying graph Preferences. Furthermore, We perform extensive experiments on cross-dataset and cross-domain settings to demonstrate the superiority of our framework. The code is available at https://github.com/OakleyTan/FedSSP.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑