How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning

• URL: http://arxiv.org/abs/2007.09370v1
• Date: Sat, 18 Jul 2020 09:06:10 GMT
• Title: How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning
• Abstract summary: We build a fair and differentially private decentralised deep learning framework called FDPDDL. It enables parties to derive more accurate local models in a fair and private manner. We show that FDPDDL achieves high fairness, yields comparable accuracy to centralised and distributed frameworks, and delivers better accuracy than the standalone framework.
• Score: 43.73144358534933
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy. A novel reputation system is proposed through digital tokens and local credibility to ensure fairness, in combination with differential privacy to guarantee privacy. In particular, we build a fair and differentially private decentralised deep learning framework called FDPDDL, which enables parties to derive more accurate local models in a fair and private manner by using our developed two-stage scheme: during the initialisation stage, artificial samples generated by Differentially Private Generative Adversarial Network (DPGAN) are used to mutually benchmark the local credibility of each party and generate initial tokens; during the update stage, Differentially Private SGD (DPSGD) is used to facilitate collaborative privacy-preserving deep learning, and local credibility and tokens of each party are updated according to the quality and quantity of individually released gradients. Experimental results on benchmark datasets under three realistic settings demonstrate that FDPDDL achieves high fairness, yields comparable accuracy to the centralised and distributed frameworks, and delivers better accuracy than the standalone framework.

Related papers

• Federated fairness-aware classification under differential privacy [9.340058165047717]
  We study the joint impact of differential privacy and fairness on classification in a federated setting.<n>We propose a two-step algorithm, namely FDP-Fair and CDP-Fair.<n>Our theoretical findings are complemented by extensive numerical experiments on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2026-03-25T15:09:12Z)
• Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification [6.28122931748758]
  We show that differential privacy can be integrated into a fairness-enhancing pipeline with minimal impact on fairness guarantees.<n>We design a postprocessing algorithm, called DP2DP, that enforces both demographic parity and differential privacy.<n>Our analysis reveals that our algorithm converges towards its demographic parity objective at essentially the same rate as the best non-private methods from the literature.
  arXiv  Detail & Related papers  (2025-11-24T08:31:02Z)
• Decentralized Differentially Private Power Method [4.58112062523768]
  We propose a novel Decentralized Differentially Private Power Method (D-DP-PM) for performing Principal Component Analysis (PCA) in networked multi-agent settings.<n>Our method ensures $(epsilon,delta)$-Differential Privacy (DP) while enabling collaborative estimation of global eigenvectors across the network.<n> Experiments on real-world datasets demonstrate that D-DP-PM achieves superior privacy-utility tradeoffs compared to naive local DP approaches.
  arXiv  Detail & Related papers  (2025-07-30T17:15:50Z)
• FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning [54.26614091429253]
  Federated instruction tuning (FedIT) is a promising solution, by consolidating collaborative training across multiple data owners. FedIT encounters limitations such as scarcity of instructional data and risk of exposure to training data extraction attacks. We propose FewFedPIT, designed to simultaneously enhance privacy protection and model performance of federated few-shot learning.
  arXiv  Detail & Related papers  (2024-03-10T08:41:22Z)
• Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond [6.731000738818571]
  Federated learning (FL) is a framework for training machine learning models in a distributed and collaborative manner. In this paper, we address the triadic interaction among personalization, privacy guarantees, and fairness attained by models trained within the FL framework. A method is put forth that introduces group privacy assurances through the utilization of $d$-privacy.
  arXiv  Detail & Related papers  (2023-09-01T12:20:19Z)
• Locally Differentially Private Distributed Online Learning with Guaranteed Optimality [1.800614371653704]
  This paper proposes an approach that ensures both differential privacy and learning accuracy in distributed online learning. While ensuring a diminishing expected instantaneous regret, the approach can simultaneously ensure a finite cumulative privacy budget. To the best of our knowledge, this is the first algorithm that successfully ensures both rigorous local differential privacy and learning accuracy.
  arXiv  Detail & Related papers  (2023-06-25T02:05:34Z)
• Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensus [11.414398732656839]
  We propose a framework that embeds differential privacy into decentralized deep learning and secures each agent's local dataset during and after cooperative training. We prove convergence guarantees for algorithms derived from this framework and demonstrate its practical utility when applied to subgradient and ADMM decentralized approaches.
  arXiv  Detail & Related papers  (2023-06-24T07:46:00Z)
• FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations [53.268801169075836]
  We propose FedLAP-DP, a novel privacy-preserving approach for federated learning. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes. Our approach presents a faster convergence speed compared to typical gradient-sharing methods.
  arXiv  Detail & Related papers  (2023-02-02T12:56:46Z)
• Differentially private partitioned variational inference [28.96767727430277]
  Learning a privacy-preserving model from sensitive data which are distributed across multiple devices is an increasingly important problem. We present differentially private partitioned variational inference, the first general framework for learning a variational approximation to a Bayesian posterior distribution.
  arXiv  Detail & Related papers  (2022-09-23T13:58:40Z)
• Differentially Private Federated Learning with Local Regularization and Sparsification [23.15611313745278]
  We study the cause of model performance degradation in federated learning under user-level DP guarantee. We propose two techniques, Bounded Local Update Regularization and Local Update Sparsification, to increase model quality without sacrificing privacy.
  arXiv  Detail & Related papers  (2022-03-07T02:48:16Z)
• Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization [57.98426940386627]
  We show that coordinating local learning with private centralized learning yields a generically useful and improved tradeoff between accuracy and privacy. We illustrate our theoretical results with experiments on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2022-02-10T20:44:44Z)
• Graph-Homomorphic Perturbations for Private Decentralized Learning [64.26238893241322]
  Local exchange of estimates allows inference of data based on private data. perturbations chosen independently at every agent, resulting in a significant performance loss. We propose an alternative scheme, which constructs perturbations according to a particular nullspace condition, allowing them to be invisible.
  arXiv  Detail & Related papers  (2020-10-23T10:35:35Z)
• Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identification [69.29602103582782]
  Deep learning has been successful for many computer vision tasks due to the availability of shared and centralised large-scale training data. However, increasing awareness of privacy concerns poses new challenges to deep learning, especially for person re-identification (Re-ID) We propose a novel paradigm called Federated Person Re-Identification (FedReID) to construct a generalisable global model (a central server) by simultaneously learning with multiple privacy-preserved local models (local clients) This client-server collaborative learning process is iteratively performed under privacy control, enabling FedReID to realise decentralised learning without sharing distributed data nor collecting any
  arXiv  Detail & Related papers  (2020-06-07T13:32:33Z)

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.