Coded Distributed Image Classification

TL;DR

This paper introduces a coded computation scheme for distributed image classification that improves fault tolerance and flexibility, enabling approximate results from any subset of workers while maintaining accuracy.

Contribution

It presents a novel coded computation scheme combining deep learning and Lagrange interpolation, with adjustable recovery thresholds and flexible system design for distributed image classification.

Findings

Outperforms existing coded computation schemes in image classification tasks

Provides adjustable recovery thresholds for system robustness

Demonstrates effective distributed inference with flexible worker participation

Abstract

In this paper, we present a coded computation (CC) scheme for distributed computation of the inference phase of machine learning (ML) tasks, specifically, the task of image classification. Building upon Agrawal et al.~2022, the proposed scheme combines the strengths of deep learning and Lagrange interpolation technique to mitigate the effect of straggling workers, and recovers approximate results with reasonable accuracy using outputs from any $R$ out of $N$ workers, where $R\leq N$. Our proposed scheme guarantees a minimum recovery threshold $R$ for non-polynomial problems, which can be adjusted as a tunable parameter in the system. Moreover, unlike existing schemes, our scheme maintains flexibility with respect to worker availability and system design. We propose two system designs for our CC scheme that allows flexibility in distributing the computational load between the master and the workers based on the accessibility of input data. Our experimental results demonstrate the superiority of our scheme compared to the state-of-the-art CC schemes for image classification tasks, and pave the path for designing new schemes for distributed computation of any general ML classification tasks.