论文标题
部分可观测时空混沌系统的无模型预测
Differentially Private Bias-Term Fine-tuning of Foundation Models
论文作者
论文摘要
我们研究了大型预训练模型的差异私有（DP）微调的问题 - 一种适合使用敏感数据解决下游任务的最新隐私方法。现有工作表明，在强大的隐私约束下，高精度是可能的，但需要对网络体系结构进行大量的计算开销或修改。我们提出了不同的私有偏见微调（DP-BITFIT），该微调与DP算法的最新精度和标准BITFIT的效率相匹配。 DP-BITFIT是模型的不可知论（不修改网络体系结构），参数有效（仅训练参数的0.1％）和计算有效的效率（几乎在时间和空间复杂性中删除了由DP引起的开销）。在各种任务上，DP-BITFIT的速度快2〜30倍，并且比DP完整微调少2〜8倍，甚至比标准完整的微调更快。这种惊人的效率使我们能够使用长期序列文本和高分辨率图像对语言和视觉任务进行微调进行微调，这些图像使用现有方法在计算上很难进行。我们在FastDP（https://github.com/awslabs/fast-differential-privacy）上开放代码。
We study the problem of differentially private (DP) fine-tuning of large pre-trained models -- a recent privacy-preserving approach suitable for solving downstream tasks with sensitive data. Existing work has demonstrated that high accuracy is possible under strong privacy constraint, yet requires significant computational overhead or modifications to the network architecture. We propose differentially private bias-term fine-tuning (DP-BiTFiT), which matches the state-of-the-art accuracy for DP algorithms and the efficiency of the standard BiTFiT. DP-BiTFiT is model agnostic (not modifying the network architecture), parameter efficient (only training about 0.1% of the parameters), and computation efficient (almost removing the overhead caused by DP, in both the time and space complexity). On a wide range of tasks, DP-BiTFiT is 2~30X faster and uses 2~8X less memory than DP full fine-tuning, even faster than the standard full fine-tuning. This amazing efficiency enables us to conduct DP fine-tuning on language and vision tasks with long-sequence texts and high-resolution images, which were computationally difficult using existing methods. We open-source our code at FastDP (https://github.com/awslabs/fast-differential-privacy).
