Federated Neural Architecture Search
This work addresses the problem of efficient neural architecture design for privacy-preserving mobile AI, representing an incremental improvement by optimizing federated NAS for resource-constrained clients.
The paper tackles the challenge of designing neural architectures for decentralized training on heterogeneous mobile platforms by proposing Federated Neural Architecture Search (FedNAS), which achieves comparable model accuracy to state-of-the-art centralized NAS algorithms and reduces client computational and communication costs by up to two orders of magnitude.
To preserve user privacy while enabling mobile intelligence, techniques have been proposed to train deep neural networks on decentralized data. However, training over decentralized data makes the design of neural architecture quite difficult as it already was. Such difficulty is further amplified when designing and deploying different neural architectures for heterogeneous mobile platforms. In this work, we propose an automatic neural architecture search into the decentralized training, as a new DNN training paradigm called Federated Neural Architecture Search, namely federated NAS. To deal with the primary challenge of limited on-client computational and communication resources, we present FedNAS, a highly optimized framework for efficient federated NAS. FedNAS fully exploits the key opportunity of insufficient model candidate re-training during the architecture search process, and incorporates three key optimizations: parallel candidates training on partial clients, early dropping candidates with inferior performance, and dynamic round numbers. Tested on large-scale datasets and typical CNN architectures, FedNAS achieves comparable model accuracy as state-of-the-art NAS algorithm that trains models with centralized data, and also reduces the client cost by up to two orders of magnitude compared to a straightforward design of federated NAS.