The emergence of foundation models, including language and vision models, has reshaped AI's landscape, offering capabilities across various applications. Deploying and fine-tuning these large models, like GPT-3 and BERT, presents challenges, especially in the current foundation model era. We introduce Emulator-Assisted Tuning (EAT) combined with Parameter-Efficient Fine-Tuning (PEFT) to form Parameter-Efficient Emulator-Assisted Tuning (PEAT). Further, we expand this into federated learning as Federated PEAT (FedPEAT). FedPEAT uses adapters, emulators, and PEFT for federated model tuning, enhancing model privacy and memory efficiency. Adapters adjust pre-trained models, while emulators give a compact representation of original models, addressing both privacy and efficiency. Adaptable to various neural networks, our approach also uses deep reinforcement learning for hyper-parameter optimization. We tested FedPEAT in a unique scenario with a server participating in collaborative federated tuning, showcasing its potential in tackling foundation model challenges.

翻译：基础模型（包括语言模型和视觉模型）的出现重塑了人工智能的格局，为各类应用提供了广泛能力。然而，在当前基础模型时代，部署和微调GPT-3、BERT等大型模型仍面临诸多挑战。我们提出模拟器辅助调优（EAT），并将其与参数高效微调（PEFT）相结合，形成参数高效模拟器辅助调优（PEAT）。进一步地，我们将此方法扩展至联邦学习场景，提出联邦PEAT（FedPEAT）。FedPEAT利用适配器、模拟器和PEFT进行联邦模型调优，从而提升模型隐私保护与内存效率。其中，适配器用于调整预训练模型，模拟器则提供原模型的紧凑表示，兼顾隐私与效率。该方法适用于各类神经网络，同时采用深度强化学习实现超参数优化。我们在一服务器参与协同联邦调优的特殊场景下测试了FedPEAT，展示了其在应对基础模型挑战方面的潜力。