.png){kind=icon}
返回
VFedCS: Optimizing Client Selection for Volatile Federated Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/JIOT.2022.3195073.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Federated learning (FL) has shown great potential as a privacy-preserving solution to training a centralized model based on local data from available clients. However, we argue that, over the course of training, the available clients may exhibit some volatility in terms of the client population, client data, and training status. Considering these volatilities, we propose a new learning scenario termed volatile federated learning (volatile FL) featuring set volatility, statistical volatility, and training volatility. The volatile client set along with the dynamic of clients' data and the unreliable nature of clients (e.g., unintentional shutdown and network instability) greatly increase the difficulty of client selection. In this article, we formulate and decompose the global problem into two subproblems based on alternating minimization. For an efficient settlement for the proposed selection problem, we quantify the impact of clients' data and resource heterogeneity for volatile FL and introduce the cumulative effective participation data (CEPD) as an optimization objective. Based on this, we propose upper confidence bound-based greedy selection, dubbed UCB-GS, to address the client selection problem in volatile FL. Theoretically, we prove that the regret of UCB-GS is strictly bounded by a finite constant, justifying its theoretical feasibility. Furthermore, experimental results show that our method significantly reduces the number of training rounds (by up to 62%) while increasing the global model's accuracy by 7.51%.
Keyword:
Client selection
combinatorial multiarm bandit (CMAB)
submodular function
volatile client
volatile federated learning (volatile FL)
期刊
IF:
8.9
论文数:
1.4W
被引数:
7.8W
机构
引用论文
Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective无线联合学习网络中的客户端选择和带宽分配: 长期观点
OAAI
OAAI分享收藏Increase in Ornithine Decarboxylase Activity Caused by Hepatocyte Growth Factor in Primary Cultured Adult Rat Hepatocytes.png)
Hepatology
HepatologyIF0
PREAI
分享收藏
查看更多内容