2023/01/28 by Haozhe Feng, Feng, Haozhe, Tianyu Pang +9 · 6 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial intelligence #Artificial neural network #Backpropagation #Code (set theory) #Computer network #Computer science #Cryptography and Data Security #Deep learning #Inference #Machine learning #Operating system #Overhead (engineering) #Privacy-Preserving Technologies in Data #Server #Set (abstract data type) #Upload
paper · pdf · doi:10.48550/arxiv.2301.12195
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/01/28 · openalex created_date 2023/02/02 · openalex updated_date 2026/07/28
Federated learning (FL) is a general principle for decentralized clients to train a server model collectively without sharing local data. FL is a promising framework with practical applications, but its standard training paradigm requires the clients to backpropagate through the model to compute gradients. Since these clients are typically edge devices and not fully trusted, executing backpropagation on them incurs computational and storage overhead as well as white-box vulnerability. In light of this, we develop backpropagation-free federated learning, dubbed BAFFLE, in which backpropagation is replaced by multiple forward processes to estimate gradients. BAFFLE is 1) memory-efficient and easily fits uploading bandwidth; 2) compatible with inference-only hardware optimization and model quantization or pruning; and 3) well-suited to trusted execution environments, because the clients in BAFFLE only execute forward propagation and return a set of scalars to the server. Empirically we use BAFFLE to train deep models from scratch or to finetune pretrained models, achieving acceptable results. Code is available in https://github.com/FengHZ/BAFFLE.