.png){kind=icon}
返回
Achieving Machine Learning Dependability Through Model Switching and Compression
.png){kind=icon}
PRE
AI
DOI：10.1109/TMC.2025.3619560.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Machine learning (ML) can be often distributed, owing to the need to harness more resources and/or to preserve privacy. Accordingly, distributed learning has received significant attention from the literature; however, most works focus on the expected learning quality (e.g., loss) attained and do not consider the distribution thereof. It follows that ML models are not dependable, and may fall short of the required performance in many real-world cases. In this work, we tackle this challenge and propose DepL, a framework attaining dependable learning orchestration: DepL efficiently makes joint, near-optimal decisions concerning (i) which data to use for learning, (ii) the ML models to use – chosen within a set of full-size models and compressed versions thereof – and when to switch from one model to another, and (iii) the clusters of physical nodes to use for the learning. DepL improves over previous works by guaranteeing that the learning quality target (e.g., a minimum loss) is achieved with a target probability, while minimizing the learning (e.g., energy) cost. DepL has provably low polynomial computational complexity and a constant competitive ratio. Further, experimental results using the CIFAR-10 and GTSRB datasets show that it consistently matches the optimum and outperforms state-of-the-art approaches (30% faster learning and 40–80% lower cost).
Keyword:
Distributed learning
network support to machine learning
dependable learning
learning guarantees
期刊
IF:
9.2
论文数:
5.6K
被引数:
1.8W
机构
引用论文
Secure Distributed/Federated Learning: Prediction-Privacy Trade-Off for Multi-Agent System安全分布式/联邦学习：多智能体系统中的预测-隐私权衡
OAAI
.png){kind=icon}
OAAI分享收藏分享收藏
查看更多内容