arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.07448cs.AIcs.LG
收藏

通过属性推理实现形式逻辑赋能的个性化联邦学习

Formal Logic Enabled Personalized Federated Learning Through Property Inference

Vanderbilt University(范德堡大学)

Ziyan An, Taylor T. Johnson, Meiyi Ma

AI总结:

针对联邦学习客户端异构且缺乏符号推理的问题,本文提出融合机械化时序逻辑表达式与聚合集群划分的个性化训练范式,并在交通和智慧城市任务中验证最高54%的准确率提升。

摘要:

联邦学习(FL)的最新进展极大地推动了去中心化协作应用的发展,尤其是在智能物联网(AIoT)领域。然而,当前研究格局中缺失的一个关键方面,是使数据驱动的客户端模型具备符号推理能力。具体而言,参与客户端设备固有的异构性带来了重大挑战,因为每个客户端都表现出独特的逻辑推理属性。若未能考虑这些设备特定的规范,可能会导致客户端预测遗漏关键属性,从而造成性能欠佳。在本工作中,我们提出一种利用时序逻辑推理来解决该问题的新型训练范式。我们的方法通过为每个 FL 客户端纳入机械化生成的逻辑表达式来增强训练过程。此外,我们引入聚合集群的概念,并开发了一种划分算法,以根据客户端时序推理属性的一致性有效地对其进行分组。我们在两项任务上评估所提出的方法:一项是由来自十五个州的传感数据组成的真实世界交通流量预测任务,另一项是利用合成数据进行的智慧城市多任务预测。评估结果展现出明显改进,在所有序列预测模型中,性能准确率最高提升达54%。

英文摘要:

Recent advancements in federated learning (FL) have greatly facilitated the development of decentralized collaborative applications, particularly in the domain of Artificial Intelligence of Things (AIoT). However, a critical aspect missing from the current research landscape is the ability to enable data-driven client models with symbolic reasoning capabilities. Specifically, the inherent heterogeneity of participating client devices poses a significant challenge, as each client exhibits unique logic reasoning properties. Failing to consider these device-specific specifications can result in critical properties being missed in the client predictions, leading to suboptimal performance. In this work, we propose a new training paradigm that leverages temporal logic reasoning to address this issue. Our approach involves enhancing the training process by incorporating mechanically generated logic expressions for each FL client. Additionally, we introduce the concept of aggregation clusters and develop a partitioning algorithm to effectively group clients based on the alignment of their temporal reasoning properties. We evaluate the proposed method on two tasks: a real-world traffic volume prediction task consisting of sensory data from fifteen states and a smart city multi-task prediction utilizing synthetic data. The evaluation results exhibit clear improvements, with performance accuracy improved by up to 54% across all sequential prediction models.

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。

↑