Heterogeneous Secure Coded Matrix Multiplication: Straggler Problem versus Information Leakage
Hongtao Zhu, Li Chen, Xiaohui Chen, Weidong Wang · 2023
Distributed computing has made it possible to satisfy the demands for large-scale matrix multiplication. A distributed computing system suffers from both straggler problem and information leakage. In a heterogeneous network consisting of worker nodes with different capacities, the straggler effect is more likely to occur on weaker nodes. While stronger nodes are supposed to compute more tasks to provide robustness, more information is leaked to them. In this paper, we propose a heterogeneous secure coded matrix multiplication (HSCMM) scheme to solve the two problems in a heterogeneous network. By taking the heterogeneity of worker nodes into consideration, the corresponding recovery threshold and security constraint are obtained. To improve the performance of such a network under the security constraint, an optimal task allocation policy is given. Numerical simulation results verify the effectiveness of our proposed scheme.