Stochastic Control Variates in WAFFLE for Efficient Federated Multimodal Inference

Abstract

This report synthesises findings from 8 peer-reviewed papers addressing the following research question: Does the stochastic control variate approach in WAFFLE improve inference efficiency and reduce latency variance in personalized multimodal models compared to standard FedAvg under straggler conditions. Federated learning (FL) is a machine learning setting where many clients (e.g., mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g., service provider), while keeping the training data decentralized. FL embodies. 10 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 7.7/10. This report is a machine-generated literature synthesis and does not constitute original research. Research goal: Does the stochastic control variate approach in WAFFLE improve inference efficiency and reduce latency variance in personalized multimodal models compared to standard FedAvg under straggler conditions? Autonomous literature synthesis. Automated review score: 7.7/10. Full text and citation available at Assignee Research.