.png){kind=icon}
返回
Coded Real Number Matrix Multiplication for On-Device Edge Computing
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2023.3326055.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This letter addresses the challenge of multiplying large real-numbered matrices A and B in on-device edge computing environments with a master node and N worker nodes. To ensure accuracy and mitigate adversarial behavior, existing approaches rely on polynomial coding techniques. However, polynomial decoding on real numbers is numerically unstable, leading prior works to employ finite fields or complex number fields. Nevertheless, computing on finite fields may encounter computation overflows. In this letter, we propose a novel, numerically stable coded matrix multiplication scheme on real number fields. Our approach detects malicious workers and mitigates the impact of slower workers (stragglers), all while operating solely on real number fields.
Keyword:
Testing
Manganese
Galois fields
Codes
Interpolation
Encoding
Numerical stability
Matrix multiplication
adversarial attacks
straggler mitigation
edge computing
internet of things
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
.png){kind=icon}
Hierarchical Group Testing for Byzantine Attack Identification in Distributed Matrix Multiplication
PREAI
分享收藏
查看更多内容