Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environments
This work addresses the need for reliable collaborative inference in safety-critical applications like environmental monitoring, where network disruptions are common, representing an incremental advance over existing vertical federated learning approaches.
The paper tackles the problem of robust collaborative inference in dynamic device networks prone to significant network failures, and presents MAGS, a method that improves robustness across various fault rates, including extreme ones, as validated by empirical results.
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.