arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.11369cs.LGcs.AI
收藏

基于基对齐和权重惩罚的联邦关系数据建模

Improving Federated Relational Data Modeling via Basis Alignment and Weight Penalty

Ant Group(蚂蚁集团)

Yilun Lin, Chaochao Chen, Cen Chen, Li Wang

摘要:

联邦学习(FL)近年来受到越来越多的关注。作为一种保护隐私的协作学习范式,它可以实现更广泛的应用,特别是对于计算机视觉和自然语言处理任务。然而,迄今为止,联邦学习在关系数据上的研究有限,即知识图谱(KG)。在这项工作中,我们提出了一个修改后的版本的图神经网络算法,在不同的参与者进行联合建模的KG。具体来说,为了解决固有的数据异构性问题和算法收敛效率低下,我们提出了一种新的优化算法,命名为FedAlign,1)最佳运输(OT)的客户端个性化和2)重量约束,以加快收敛。在几个广泛使用的数据集上进行了大量的实验。实验结果表明,我们提出的方法优于最先进的FL方法,如FedAVG和FedProx,具有更好的收敛性。

英文摘要:

Federated learning (FL) has attracted increasing attention in recent years. As a privacy-preserving collaborative learning paradigm, it enables a broader range of applications, especially for computer vision and natural language processing tasks. However, to date, there is limited research of federated learning on relational data, namely Knowledge Graph (KG). In this work, we present a modified version of the graph neural network algorithm that performs federated modeling over KGs across different participants. Specifically, to tackle the inherent data heterogeneity issue and inefficiency in algorithm convergence, we propose a novel optimization algorithm, named FedAlign, with 1) optimal transportation (OT) for on-client personalization and 2) weight constraint to speed up the convergence. Extensive experiments have been conducted on several widely used datasets. Empirical results show that our proposed method outperforms the state-of-the-art FL methods, such as FedAVG and FedProx, with better convergence.

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。

↑