FDNAS: Improving Data Privacy and Model Diversity in AutoML

Abstract

To prevent the leakage of private information while enabling automated machine intelligence, there is an emerging trend to integrate federated learning and Neural Architecture Search (NAS). Although promising as it may seem, the coupling of difficulties from both two tenets makes the algorithm development quite challenging. In particular, how to efficiently search the optimal neural architecture directly from massive non-iid data of clients in a federated manner remains to be a hard nut to crack. To tackle this challenge, in this paper, by leveraging the advances in proxy-less NAS, we propose a Federated Direct Neural Architecture Search (FDNAS) framework that allows hardware-aware NAS from decentralized non-iid data of clients. To further adapt for various data distributions of clients, inspired by meta-learning, a cluster Federated Direct Neural Architecture Search (CFDNAS) framework is proposed to achieve client-aware NAS, in the sense that each client can learn a tailored deep learning model for its particular data distribution. Extensive experiments on real-world non-iid datasets show state-of-the-art accuracy-efficiency trade-offs for various hardware and data distributions of clients. Our codes will be released publicly upon paper acceptance.

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Federated Learning with Non-IID Data
• On the Convergence of FedAvg on Non-IID Data
• Efficient Neural Architecture Search via Parameter Sharing
• Differentially Private Federated Learning: A Client Level Perspective
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• SNAS: Stochastic Neural Architecture Search
• Hierarchical Representations for Efficient Architecture Search
• A Closer Look at Few-shot Classification
• Distributed Mean Estimation with Limited Communication
• Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search