Private Federated Learning using Preference-Optimized Synthetic Data

• URL: http://arxiv.org/abs/2504.16438v1
• Date: Wed, 23 Apr 2025 05:57:20 GMT
• Title: Private Federated Learning using Preference-Optimized Synthetic Data
• Authors: Charlie Hou, Mei-Yu Wang, Yige Zhu, Daniel Lazar, Giulia Fanti,
• Abstract summary: In practical settings, differentially private Federated learning (DP-FL) is the dominant method for training models from private, on-device client data.<n>Recent work has suggested that DP-FL may be enhanced or outperformed by methods that use DP synthetic data.<n>Our key insight is that the private client feedback collected by prior DP synthetic data methods can be viewed as a preference ranking.
• Score: 10.143621632256448
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In practical settings, differentially private Federated learning (DP-FL) is the dominant method for training models from private, on-device client data. Recent work has suggested that DP-FL may be enhanced or outperformed by methods that use DP synthetic data (Wu et al., 2024; Hou et al., 2024). The primary algorithms for generating DP synthetic data for FL applications require careful prompt engineering based on public information and/or iterative private client feedback. Our key insight is that the private client feedback collected by prior DP synthetic data methods (Hou et al., 2024; Xie et al., 2024) can be viewed as a preference ranking. Our algorithm, Preference Optimization for Private Client Data (POPri) harnesses client feedback using preference optimization algorithms such as Direct Preference Optimization (DPO) to fine-tune LLMs to generate high-quality DP synthetic data. To evaluate POPri, we release LargeFedBench, a new federated text benchmark for uncontaminated LLM evaluations on federated client data. POPri substantially improves the utility of DP synthetic data relative to prior work on LargeFedBench datasets and an existing benchmark from Xie et al. (2024). POPri closes the gap between next-token prediction accuracy in the fully-private and non-private settings by up to 68%, compared to 52% for prior synthetic data methods, and 10% for state-of-the-art DP federated learning methods. The code and data are available at https://github.com/meiyuw/POPri.

Related papers

• Synthesizing Privacy-Preserving Text Data via Finetuning without Finetuning Billion-Scale LLMs [20.774525687291167]
  We propose a novel framework for generating privacy-preserving synthetic data without extensive prompt engineering or billion-scale finetuning. CTCL pretrains a lightweight 140M conditional generator and a clustering-based topic model on large-scale public data. To further adapt to the private domain, the generator is DP finetuned on private data for fine-grained textual information, while the topic model extracts a DP histogram.
  arXiv  Detail & Related papers  (2025-03-16T04:00:32Z)
• Is API Access to LLMs Useful for Generating Private Synthetic Tabular Data? [19.72500788849435]
  Differentially private (DP) synthetic data is a versatile tool for enabling the analysis of private data.<n>Recent advancements in large language models (LLMs) have inspired a number of algorithm techniques for improving DP synthetic data generation.<n>One family of approaches uses DP finetuning on the foundation model weights; however, the model weights for state-of-the-art models may not be public.
  arXiv  Detail & Related papers  (2025-02-10T15:23:52Z)
• Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models with human preferences.<n>Our key idea is leveraging the human prior knowledge within the small (seed) data.<n>We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)
• Prompt Public Large Language Models to Synthesize Data for Private On-device Applications [5.713077600587505]
  This paper investigates how large language models (LLMs) trained on public data can improve the quality of pre-training data for the on-device language models trained with DP and FL. The model pre-trained on our synthetic dataset achieves relative improvement of 19.0% and 22.8% in next word prediction accuracy. Our experiments demonstrate the strengths of LLMs in synthesizing data close to the private distribution even without accessing the private data.
  arXiv  Detail & Related papers  (2024-04-05T19:14:14Z)
• Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
  We propose a new axis based on eliciting preferences jointly over instruction-response pairs.<n>Joint preferences over instruction and response pairs can significantly enhance the alignment of large language models.
  arXiv  Detail & Related papers  (2024-03-31T02:05:40Z)
• 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)
• Benchmarking Private Population Data Release Mechanisms: Synthetic Data vs. TopDown [50.40020716418472]
  This study conducts a comparison between the TopDown algorithm and private synthetic data generation to determine how accuracy is affected by query complexity. Our results show that for in-distribution queries, the TopDown algorithm achieves significantly better privacy-fidelity tradeoffs than any of the synthetic data methods we evaluated.
  arXiv  Detail & Related papers  (2024-01-31T17:38:34Z)
• Harnessing large-language models to generate private synthetic text [18.863579044812703]
  Differentially private training algorithms like DP-SGD protect sensitive training data by ensuring that trained models do not reveal private information. This paper studies an alternative approach to generate synthetic data that is differentially private with respect to the original data, and then non-privately training a model on the synthetic data. generating private synthetic data is much harder than training a private model.
  arXiv  Detail & Related papers  (2023-06-02T16:59:36Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• Privately Customizing Prefinetuning to Better Match User Data in Federated Learning [3.645000701985685]
  In Federated Learning (FL), accessing private client data incurs communication and privacy costs. We propose FreD (Federated Private Fr'echet Distance) -- a privately computed distance between a prefinetuning dataset and federated datasets. We show empirically that FreD accurately predicts the best prefinetuning dataset at minimal privacy cost.
  arXiv  Detail & Related papers  (2023-02-17T18:18:22Z)
• Practical Differentially Private Hyperparameter Tuning with Subsampling [8.022555128083026]
  We propose a new class of differentially private (DP) machine learning (ML) algorithms, where the number of random search samples is randomized itself. We focus on lowering both the DP bounds and the computational cost of these methods by using only a random subset of the sensitive data. We provide a R'enyi differential privacy analysis for the proposed method and experimentally show that it consistently leads to better privacy-utility trade-off.
  arXiv  Detail & Related papers  (2023-01-27T21:01:58Z)
• User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization [77.43075255745389]
  Federated learning (FL) is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. From a viewpoint of information theory, it is still possible for a curious server to infer private information from the shared models uploaded by MTs. We propose a user-level differential privacy (UDP) algorithm by adding artificial noise to the shared models before uploading them to servers.
  arXiv  Detail & Related papers  (2020-02-29T10:13:39Z)

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.