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（包括语言和视觉模型）的出现重塑了人工智能格局，为各类应用提供了强大能力。然而，在当前基础模型时代，部署和微调GPT-3、BERT等大型模型带来了诸多挑战。我们提出了仿真器辅助调优（EAT）与参数高效微调（PEFT）相结合的方法，形成参数高效仿真器辅助调优（PEAT）。进一步地，我们将该方法扩展至联邦学习场景，提出联邦PEAT（FedPEAT）。FedPEAT利用适配器、仿真器和PEFT进行联邦模型调优，增强了模型隐私性和内存效率。适配器用于调整预训练模型，而仿真器则提供原始模型的紧凑表示，兼顾隐私与效率。该方法可适配各类神经网络，并采用深度强化学习进行超参数优化。我们在服务器参与协作联邦调优的独特场景下测试了FedPEAT，展示了其在应对基础模型挑战方面的潜力。