.png){kind=icon}
返回
Differentially Private Federated Learning With Importance Client Sampling
.png){kind=icon}
PRE
AI
DOI：10.1109/TCE.2023.3338464.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As numerous consumer electronics applications like smartphones and wearables generate lots of distributed data daily, consumers desire to safely and efficiently tackle private and isolated data. Federated learning (FL) is hopeful to satisfy the above requirement due to strong data security and applicability to large-scale scenarios. But diverse clients inevitably cause non-independent and identically distributed (non-iid) data among clients, which severely hinders performance analysis. Besides, affected by non-iid data, the participating clients are typically heterogeneous, which induces the client sampling problem. More importantly, albeit FL can enhance privacy via data localization, for highly secret data like physiological data from wearables, FL should possess stronger security to prevent third-party attacks. For data heterogeneity, client sampling, and privacy security, we propose differential privacy (DP) enabled and importance-aware FL algorithm DPFLICS to jointly handle these problems. Specifically, we utilize the truncated concentrated DP to tightly track the end-to-end privacy loss. To attain better sampling, the server selects partial clients with the probability derived from our importance client sampling. Moreover, to further improve performance, we also leverage the adaptive YOGI optimizer on the server side, which is an adaptive gradient method improved from the widely-used ADAM optimization. Finally, the multiple experiments exhibit the effectiveness of our method.
Keyword:
Servers
Distributed databases
Consumer electronics
Privacy
Convergence
Data models
Federated learning
federated learning
differential privacy
client sampling
adaptive optimization
期刊
IF:
10.9
论文数:
5.4K
被引数:
6.8K
机构
暂无机构信息
引用论文
.png){kind=icon}
Towards Efficient and Stable K-Asynchronous Federated Learning With Unbounded Stale Gradients on Non-IID Data在非IID数据上实现具有无界陈旧梯度的高效稳定的K异步联合学习
OAAI
OAAI分享收藏分享收藏Crowd Counting by Using Top-k Relations: A Mixed Ground-Truth CNN Framework使用Top-k关系进行人群计数: 混合地面真相CNN框架
PREAI
分享收藏分享收藏FedLearnSP: Preserving Privacy and Security Using Federated Learning and Edge ComputingFedLearnSP: 使用联合学习和边缘计算保护隐私和安全
PREAI
分享收藏Secure-Enhanced Federated Learning for AI-Empowered Electric Vehicle Energy Prediction安全增强的联合学习，用于AI支持的电动汽车能量预测
PREAI
分享收藏
查看更多内容