English
Related papers

Related papers: Large-Scale Differentially Private BERT

200 papers

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the…

Computation and Language · Computer Science 2022-12-02 Zhengfu He , Tianxiang Sun , Kuanning Wang , Xuanjing Huang , Xipeng Qiu

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input…

Computation and Language · Computer Science 2021-02-09 Sanqiang Zhao , Raghav Gupta , Yang Song , Denny Zhou

Differentially private stochastic gradient descent (DP-SGD) is a standard approach to privacy-preserving learning based on per-example clipping, subsampling, Gaussian perturbation, and privacy accounting. Classical DP-SGD releases a noisy…

Cryptography and Security · Computer Science 2026-05-12 Mohammad Partohaghighi , Roummel Marcia

The pre-training and fine-tuning paradigm has contributed to a number of breakthroughs in Natural Language Processing (NLP). Instead of directly training on a downstream task, language models are first pre-trained on large datasets with…

Machine Learning · Computer Science 2023-08-01 Vithursan Thangarasa , Abhay Gupta , William Marshall , Tianda Li , Kevin Leong , Dennis DeCoste , Sean Lie , Shreyas Saxena

This paper focuses on the problem of Differentially Private Stochastic Optimization for (multi-layer) fully connected neural networks with a single output node. In the first part, we examine cases with no hidden nodes, specifically focusing…

Machine Learning · Computer Science 2023-10-13 Hanpu Shen , Cheng-Long Wang , Zihang Xiang , Yiming Ying , Di Wang

Stochastic gradient descent (SGD) is almost ubiquitously used for training non-convex optimization tasks. Recently, a hypothesis proposed by Keskar et al. [2017] that large batch methods tend to converge to sharp minimizers has received…

Machine Learning · Statistics 2018-12-04 Xiaowu Dai , Yuhua Zhu

Deep neural networks often use large, high-quality datasets to achieve high performance on many machine learning tasks. When training involves potentially sensitive data, this process can raise privacy concerns, as large models have been…

Machine Learning · Computer Science 2025-06-23 Felix Zhou , Samson Zhou , Vahab Mirrokni , Alessandro Epasto , Vincent Cohen-Addad

BERT (Bidirectional Encoder Representations from Transformers) has revolutionized the field of natural language processing through its exceptional performance on numerous tasks. Yet, the majority of researchers have mainly concentrated on…

Computation and Language · Computer Science 2024-12-11 Wen Liang , Youzhi Liang

Large language models (LLMs) have revolutionized lots of fields of research. Although it is well-known that fine-tuning is essential for enhancing the capabilities of LLMs, existing research suggests that there is potential redundancy in…

Artificial Intelligence · Computer Science 2025-02-14 Haoling Li , Xin Zhang , Xiao Liu , Yeyun Gong , Yifan Wang , Qi Chen , Peng Cheng

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Yu-Lin Tsai , Yizhe Li , Zekai Chen , Po-Yu Chen , Chia-Mu Yu , Xuebin Ren , Francois Buet-Golfouse

Large-scale distributed training of deep acoustic models plays an important role in today's high-performance automatic speech recognition (ASR). In this paper we investigate a variety of asynchronous decentralized distributed training…

Computation and Language · Computer Science 2021-10-22 Xiaodong Cui , Wei Zhang , Abdullah Kayi , Mingrui Liu , Ulrich Finkler , Brian Kingsbury , George Saon , David Kung

Transformer-based pre-trained language models, such as BERT, achieve great success in various natural language understanding tasks. Prior research found that BERT captures a rich hierarchy of linguistic information at different layers.…

Computation and Language · Computer Science 2023-07-17 Qian Chen , Wen Wang , Qinglin Zhang , Chong Deng , Ma Yukun , Siqi Zheng

Differentially Private Stochastic Gradient Descent (DP-SGD) is a cornerstone technique for ensuring privacy in deep learning, widely used in both training from scratch and fine-tuning large-scale language models. While DP-SGD predominantly…

Cryptography and Security · Computer Science 2026-03-10 Meisam Mohammady , Qin Yang , Nicholas Stout , Ayesha Samreen , Han Wang , Christopher J Quinn , Yuan Hong

Recent advances have substantially improved the accuracy, memory cost, and training speed of differentially private (DP) deep learning, especially on large vision and language models with millions to billions of parameters. In this work, we…

Machine Learning · Computer Science 2023-10-31 Zhiqi Bu , Ruixuan Liu , Yu-Xiang Wang , Sheng Zha , George Karypis

Modern deep networks are trained with stochastic gradient descent (SGD) whose key hyperparameters are the number of data considered at each step or batch size $B$, and the step size or learning rate $\eta$. For small $B$ and large $\eta$,…

Machine Learning · Computer Science 2024-02-29 Antonio Sclocchi , Matthieu Wyart

This paper presents an improved LLM based model for Grammatical Error Detection (GED), which is a very challenging and equally important problem for many applications. The traditional approach to GED involved hand-designed features, but…

Computation and Language · Computer Science 2024-11-26 Rahul Nihalani , Kushal Shah

We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable,…

Computation and Language · Computer Science 2024-05-24 Aldo Gael Carranza , Rezsa Farahani , Natalia Ponomareva , Alex Kurakin , Matthew Jagielski , Milad Nasr

This paper considers the generalization performance of differentially private convex learning. We demonstrate that the convergence analysis of Langevin algorithms can be used to obtain new generalization bounds with differential privacy…

Machine Learning · Computer Science 2022-06-07 Yi-An Ma , Teodor Vanislavov Marinov , Tong Zhang

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

Machine Learning · Computer Science 2025-10-29 Miguel Fernandez-de-Retana , Unai Zulaika , Rubén Sánchez-Corcuera , Aitor Almeida

Deep learning thrives with large neural networks and large datasets. However, larger networks and larger datasets result in longer training times that impede research and development progress. Distributed synchronous SGD offers a potential…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Priya Goyal , Piotr Dollár , Ross Girshick , Pieter Noordhuis , Lukasz Wesolowski , Aapo Kyrola , Andrew Tulloch , Yangqing Jia , Kaiming He