FDNAS: Improving Data Privacy and Model Diversity in AutoML
This work addresses data privacy and model diversity issues in AutoML for clients with non-iid data, representing an incremental improvement by integrating federated learning and NAS with meta-learning adaptations.
The paper tackles the challenge of efficiently searching for optimal neural architectures from decentralized, non-iid client data in federated learning, proposing FDNAS and CFDNAS frameworks that achieve state-of-the-art accuracy-efficiency trade-offs on real-world datasets.
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.