用模糊认知图解决联邦学习中数据分布差异问题
Concurrent vertical and horizontal federated learning with fuzzy cognitive maps
- 引入模糊认知图建模多方数据特征关系
- 四种加权策略下模型性能均优于传统方法
- 适合医疗金融等隐私敏感领域的联邦学习
数据隐私是医疗、金融等行业面临的核心挑战，保护隐私可避免数据泄露和滥用带来的严重后果。联邦学习是一种分布式机器学习方法，允许多方在不共享原始数据的前提下协同训练模型。然而，参与者间特征空间差异（非同质分布数据）带来了显著挑战。本文提出一种基于模糊认知图的新型联邦学习框架，旨在全面应对异构数据分布与非同质特征带来的问题。通过四组不同联邦策略（基于常量、准确率、AUC、精确率的权重）进行实验验证，结果表明该方法在保障隐私与保密性的前提下，有效实现了预期学习效果。
原文摘要 · Abstract (English)
Data privacy is a major concern in industries such as healthcare or finance. The requirement to safeguard privacy is essential to prevent data breaches and misuse, which can have severe consequences for individuals and organisations. Federated learning is a distributed machine learning approach where multiple participants collaboratively train a model without compromising the privacy of their data. However, a significant challenge arises from the differences in feature spaces among participants, known as non-IID data. This research introduces a novel federated learning framework employing fuzzy cognitive maps, designed to comprehensively address the challenges posed by diverse data distributions and non-identically distributed features in federated settings. The proposal is tested through several experiments using four distinct federation strategies: constant-based, accuracy-based, AUC-based, and precision-based weights. The results demonstrate the effectiveness of the approach in achieving the desired learning outcomes while maintaining privacy and confidentiality standards.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。