paper-with-me

Papers

Differentially Private Learning Needs Better Model Initialization and Self-Distillation

2024-10-23 · Ivoline C. Ngong, Joseph P. Near, Niloofar Mireshghallah

Differentially private SGD (DPSGD) enables privacy-preserving training of language models, but often reduces utility, diversity, and linguistic quality. We introduce DPRefine, a three-phase method that initializes a model using data synthesis from a small pre-trained LM with rigorous filtering, applies DP finetuning on private data, and performs self-distillation to refine outputs. This approach significantly outperforms vanilla DPSGD, with AlpacaEval preferring DPRefine's generations in 78.4% of cases across all datasets. Our analysis reveals that DPRefine reduces linguistic errors in generated text by 84.0%, mitigating grammar and spelling errors, commonly associated with DPSGD. It also reduces inconsistencies of non-private models, such as hallucinated details and misattributed quotes. We find that small models like GPT-2 can be effective for initialization and distillation, highlighting their potential in enabling scalable and efficient deployment of privacy-preserving language.

📄 PDF Abstract BibTeX arXiv:2410.17566

Code (1)

uvm-plaid/private_llm_generation 공식 구현 pytorch

Tasks

DiversityPrivacy Preserving

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…

Similar Papers 제목 키워드 기반

The role of self-supervised pretraining in differentially private medical image analysis

2026-01-27 · Soroosh Tayebi Arasteh, Mina Farajiamiri, Mahshad Lotfinia, Behrus Hinrichs-Puladi 외 arxiv

Differential privacy (DP) provides formal protection for sensitive data but typically incurs substantial losses in diagnostic performance. Model initialization has emerged as a critical factor in mitigating this degradat…

Self-Supervised Learning

Differentially Private Learning Needs Better Features (or Much More Data)

2020-11-23 · ICLR 2021 1 · Florian Tramèr, Dan Boneh

We demonstrate that differentially private machine learning has not yet reached its "AlexNet moment" on many canonical vision tasks: linear models trained on handcrafted features significantly outperform end-to-end deep …

BIG-bench Machine Learning

Near-Optimal differentially private low-rank trace regression with guaranteed private initialization

2024-03-24 · Mengyue Zha

We study differentially private (DP) estimation of a rank-$r$ matrix $M \in \RR^{d_1\times d_2}$ under the trace regression model with Gaussian measurement matrices. Theoretically, the sensitivity of non-private spectral…

regressionRiemannian optimizationSensitivity

Representation Transfer for Differentially Private Drug Sensitivity Prediction

2019-01-29 · Teppo Niinimäki, Mikko Heikkilä, Antti Honkela, Samuel Kaski

Motivation: Human genomic datasets often contain sensitive information that limits use and sharing of the data. In particular, simple anonymisation strategies fail to provide sufficient level of protection for genomic da…

BIG-bench Machine LearningCancer type classificationDimensionality ReductionPrediction+2

On the Intrinsic Differential Privacy of Bagging

2020-08-22 · Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

Differentially private machine learning trains models while protecting privacy of the sensitive training data. The key to obtain differentially private models is to introduce noise/randomness to the training process. In …

BIG-bench Machine LearningEnsemble Learning