Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environments

TL;DR

This paper introduces MAGS, a robust collaborative inference method for vertically split data across dynamic device networks, effectively handling significant network failures in safety-critical applications.

Contribution

The paper formalizes the problem of robust collaborative inference over dynamic, fault-prone networks and proposes MAGS, a novel method that synthesizes simulated faults to enhance robustness.

Findings

MAGS significantly outperforms baseline methods under various fault rates.

MAGS maintains high accuracy even at extreme fault rates.

Theoretical analysis explains the robustness benefits of each component.

Abstract

When each edge device of a network only perceives a local part of the environment, collaborative inference across multiple devices is often needed to predict global properties of the environment. In safety-critical applications, collaborative inference must be robust to significant network failures caused by environmental disruptions or extreme weather. Existing collaborative learning approaches, such as privacy-focused Vertical Federated Learning (VFL), typically assume a centralized setup or that one device never fails. However, these assumptions make prior approaches susceptible to significant network failures. To address this problem, we first formalize the problem of robust collaborative inference over a dynamic network of devices that could experience significant network faults. Then, we develop a minimalistic yet impactful method called Multiple Aggregation with Gossip Rounds and Simulated Faults (MAGS) that synthesizes simulated faults via dropout, replication, and gossiping to significantly improve robustness over baselines. We also theoretically analyze our proposed approach to explain why each component enhances robustness. Extensive empirical results validate that MAGS is robust across a range of fault rates-including extreme fault rates.