Keywords: AutoML, Federated Learning, Deep Neural Networks, Model Compression
TL;DR: We introduce AutoFLIP, an automatic informed pruning strategy for federated learning.
Abstract: Federated learning (FL) represents a pivotal shift in machine learning (ML) as it enables collaborative training of local ML models coordinated by a central aggregator, all without the need to exchange local data. However, its application on edge devices is hindered by limited computational capabilities and data communication challenges, compounded by the inherent complexity of Deep Learning (DL) models. Model pruning is identified as a key technique for compressing DL models on devices with limited resources. Nonetheless, conventional pruning techniques typically rely on manually crafted heuristics and demand human expertise to achieve a balance between model size, speed, and accuracy, often resulting in sub-optimal solutions.
In this study, we introduce an automated federated learning approach utilizing informed pruning, called AutoFLIP, which dynamically prunes and compresses DL models within both the local clients and the global server. It leverages a federated loss exploration phase to investigate model gradient behavior across diverse datasets and losses, providing insights into parameter significance. Our experiments showcase notable enhancements in scenarios with strong non-IID data, underscoring AutoFLIP's capacity to tackle computational constraints and achieve superior global convergence.
Submission Checklist: Yes
Broader Impact Statement: Yes
Paper Availability And License: Yes
Code Of Conduct: Yes
Optional Meta-Data For Green-AutoML: This blue field is just for structuring purposes and cannot be filled.
Submission Number: 28
Loading