CoCoI: Distributed Coded Inference System for Straggler Mitigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Xing, Huang, Chao, Tang, Ming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910781203808256
author Liu, Xing
Huang, Chao
Tang, Ming
author_facet Liu, Xing
Huang, Chao
Tang, Ming
contents Convolutional neural networks (CNNs) are widely applied in real-time applications on resource-constrained devices. To accelerate CNN inference, prior works proposed to distribute the inference workload across multiple devices. However, they did not address stragglers and device failures in distributed inference, which is challenging due to the devices' time-varying and possibly unknown computation/communication capacities. To address this, we propose a distributed coded inference system, called CoCoI. It splits the convolutional layers of CNN, considering the data dependency of high-dimensional inputs and outputs, and then adapts coding schemes to generate task redundancy. With CoCoI, the inference results can be determined once a subset of devices complete their subtasks, improving robustness against stragglers and failures. To theoretically analyze the tradeoff between redundancy and subtask workload, we formulate an optimal splitting problem to minimize the expected inference latency. Despite its non-convexity, we determine an approximate strategy with minor errors, and prove that CoCoI outperforms uncoded benchmarks. For performance evaluation, we build a testbed with Raspberry Pi 4Bs. The experimental results show that the approximate strategy closely matches the optimal solution. When compared with uncoded benchmarks, CoCoI reduces inference latency by up to 34.2% in the presence of stragglers and device failures.
format Preprint
id arxiv_https___arxiv_org_abs_2501_06856
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoCoI: Distributed Coded Inference System for Straggler Mitigation
Liu, Xing
Huang, Chao
Tang, Ming
Distributed, Parallel, and Cluster Computing
Convolutional neural networks (CNNs) are widely applied in real-time applications on resource-constrained devices. To accelerate CNN inference, prior works proposed to distribute the inference workload across multiple devices. However, they did not address stragglers and device failures in distributed inference, which is challenging due to the devices' time-varying and possibly unknown computation/communication capacities. To address this, we propose a distributed coded inference system, called CoCoI. It splits the convolutional layers of CNN, considering the data dependency of high-dimensional inputs and outputs, and then adapts coding schemes to generate task redundancy. With CoCoI, the inference results can be determined once a subset of devices complete their subtasks, improving robustness against stragglers and failures. To theoretically analyze the tradeoff between redundancy and subtask workload, we formulate an optimal splitting problem to minimize the expected inference latency. Despite its non-convexity, we determine an approximate strategy with minor errors, and prove that CoCoI outperforms uncoded benchmarks. For performance evaluation, we build a testbed with Raspberry Pi 4Bs. The experimental results show that the approximate strategy closely matches the optimal solution. When compared with uncoded benchmarks, CoCoI reduces inference latency by up to 34.2% in the presence of stragglers and device failures.
title CoCoI: Distributed Coded Inference System for Straggler Mitigation
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2501.06856