Sparsity-Preserving Differentially Private Training of Large Embedding
Models
- URL: http://arxiv.org/abs/2311.08357v1
- Date: Tue, 14 Nov 2023 17:59:51 GMT
- Title: Sparsity-Preserving Differentially Private Training of Large Embedding
Models
- Authors: Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin
Manurangsi, Amer Sinha, Chiyuan Zhang
- Abstract summary: 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.
- Score: 67.29926605156788
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: As the use of large embedding models in recommendation systems and language
applications increases, concerns over user data privacy have also risen.
DP-SGD, a training algorithm that combines differential privacy with stochastic
gradient descent, has been the workhorse in protecting user privacy without
compromising model accuracy by much. However, applying DP-SGD naively to
embedding models can destroy gradient sparsity, leading to reduced training
efficiency. To address this issue, we present two new algorithms, DP-FEST and
DP-AdaFEST, that preserve gradient sparsity during private training of large
embedding models. Our algorithms achieve substantial reductions ($10^6 \times$)
in gradient size, while maintaining comparable levels of accuracy, on benchmark
real-world datasets.
Related papers
- Private Fine-tuning of Large Language Models with Zeroth-order
Optimization [54.24600476755372]
We introduce DP-ZO, a new method for fine-tuning large language models that preserves the privacy of training data by privatizing zeroth-order optimization.
We show that DP-ZO exhibits just $1.86%$ performance degradation due to privacy at $ (1,10-5)$-DP when fine-tuning OPT-66B on 1000 training samples from SQuAD.
arXiv Detail & Related papers (2024-01-09T03:53:59Z) - Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in
Private SGD [56.01810892677744]
We show a connection between per-sample gradient norms and the estimation bias of the private gradient oracle used in DP-SGD.
We propose Bias-Aware Minimisation (BAM) that allows for the provable reduction of private gradient estimator bias.
arXiv Detail & Related papers (2023-08-23T09:20:41Z) - 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) - Large Language Models Can Be Strong Differentially Private Learners [70.0317718115406]
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.
arXiv Detail & Related papers (2021-10-12T01:45:27Z) - 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) - Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for
Private Learning [74.73901662374921]
A differentially private model degrades the utility drastically when the model comprises a large number of trainable parameters.
We propose an algorithm emphGradient Embedding Perturbation (GEP) towards training differentially private deep models with decent accuracy.
arXiv Detail & Related papers (2021-02-25T04:29:58Z) - Improving Deep Learning with Differential Privacy using Gradient
Encoding and Denoising [36.935465903971014]
In this paper, we aim at training deep learning models with differential privacy guarantees.
Our key technique is to encode gradients to map them to a smaller vector space.
We show that our mechanism outperforms the state-of-the-art DPSGD.
arXiv Detail & Related papers (2020-07-22T16:33:14Z)
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.