Large Language Models Can Be Strong Differentially Private Learners

• URL: http://arxiv.org/abs/2110.05679v1
• Date: Tue, 12 Oct 2021 01:45:27 GMT
• Title: Large Language Models Can Be Strong Differentially Private Learners
• Authors: Xuechen Li, Florian Tram\`er, Percy Liang, Tatsunori Hashimoto
• Abstract summary: Differentially Private (DP) learning has seen limited success for building large deep learning models of text. We show that this performance drop can be mitigated with the use of large pretrained models. We propose a memory saving technique that allows clipping in DP-SGD to run without instantiating per-example gradients.
• Score: 70.0317718115406
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Differentially Private (DP) learning has seen limited success for building large deep learning models of text, and attempts at straightforwardly applying Differentially Private Stochastic Gradient Descent (DP-SGD) to NLP tasks have resulted in large performance drops and high computational overhead. We show that this performance drop can be mitigated with (1) the use of large pretrained models; (2) hyperparameters that suit DP optimization; and (3) fine-tuning objectives aligned with the pretraining procedure. With these factors set right, we obtain private NLP models that outperform state-of-the-art private training approaches and strong non-private baselines -- by directly fine-tuning pretrained models with DP optimization on moderately-sized corpora. To address the computational challenge of running DP-SGD with large Transformers, we propose a memory saving technique that allows clipping in DP-SGD to run without instantiating per-example gradients for any layer in the model. The technique enables privately training Transformers with almost the same memory cost as non-private training at a modest run-time overhead. Contrary to conventional wisdom that DP optimization fails at learning high-dimensional models (due to noise that scales with dimension) empirical results reveal that private learning with pretrained models tends to not suffer from dimension-dependent performance degradation.

Related papers

• DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction [57.83978915843095]
  This paper introduces DiSK, a novel framework designed to significantly enhance the performance of differentially private gradients. To ensure practicality for large-scale training, we simplify the Kalman filtering process, minimizing its memory and computational demands.
  arXiv  Detail & Related papers  (2024-10-04T19:30:39Z)
• Pre-training Differentially Private Models with Limited Public Data [54.943023722114134]
  differential privacy (DP) is a prominent method to gauge the degree of security provided to the models. DP is yet not capable of protecting a substantial portion of the data used during the initial pre-training stage. We develop a novel DP continual pre-training strategy using only 10% of public data. Our strategy can achieve DP accuracy of 41.5% on ImageNet-21k, as well as non-DP accuracy of 55.7% and and 60.0% on downstream tasks Places365 and iNaturalist-2021.
  arXiv  Detail & Related papers  (2024-02-28T23:26:27Z)
• Private Fine-tuning of Large Language Models with Zeroth-order Optimization [51.19403058739522]
  Differentially private gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner. We introduce DP-ZO, a private fine-tuning framework for large language models by privatizing zeroth order optimization methods.
  arXiv  Detail & Related papers  (2024-01-09T03:53:59Z)
• Sparsity-Preserving Differentially Private Training of Large Embedding Models [67.29926605156788]
  DP-SGD is a training algorithm that combines differential privacy with gradient descent. Applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. We present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models.
  arXiv  Detail & Related papers  (2023-11-14T17:59:51Z)
• Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models [7.49320945341034]
  We show that small and efficient architecture design can outperform current state-of-the-art models with substantially lower computational requirements. Our results are a step towards efficient model architectures that make optimal use of their parameters.
  arXiv  Detail & Related papers  (2023-01-30T17:43:47Z)
• Large Scale Transfer Learning for Differentially Private Image Classification [51.10365553035979]
  Differential Privacy (DP) provides a formal framework for training machine learning models with individual example level privacy. Private training using DP-SGD protects against leakage by injecting noise into individual example gradients. While this result is quite appealing, the computational cost of training large-scale models with DP-SGD is substantially higher than non-private training.
  arXiv  Detail & Related papers  (2022-05-06T01:22:20Z)
• An Efficient DP-SGD Mechanism for Large Scale NLP Models [28.180412581994485]
  Data used to train Natural Language Understanding (NLU) models may contain private information such as addresses or phone numbers. It is desirable that underlying models do not expose private information contained in the training data. Differentially Private Gradient Descent (DP-SGD) has been proposed as a mechanism to build privacy-preserving models.
  arXiv  Detail & Related papers  (2021-07-14T15:23:27Z)
• DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing [0.0]
  We propose DPlis--Differentially Private Learning wIth Smoothing. We show that DPlis can effectively boost model quality and training stability under a given privacy budget.
  arXiv  Detail & Related papers  (2021-03-02T06:33:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.