mlsanityData to 14 Oct 2026

Differentially Private Meta-Learning

arXiv 1909.05830 ↗First posted 12 Sep 2019cs.LG cs.AI cs.CRcited by 41

Not on the map. Why?

Abstract (arXiv)

Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models that have been trained on the samples from specific tasks, thus leaving the task-owners susceptible to breaches of privacy. We conduct the first formal study of privacy in this setting and formalize the notion of task-global differential privacy as a practical relaxation of more commonly studied threat models. We then propose a new differentially private algorithm for gradient-based parameter transfer that not only satisfies this privacy requirement but also retains provable transfer learning guarantees in convex settings. Empirically, we apply our analysis to the problems of federated learning with personalization and few-shot classification, showing that allowing the relaxation to task-global privacy from the more commonly studied notion of local privacy leads to dramatically increased performance in recurrent neural language modeling and image classification.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 9; 2023: 4; 2024: 7; 2025: 4; 2026: 2.

41 papers.

Sort:

By area:

  1. 2021A Field Guide to Federated Optimizationcited by 315
  2. 2021Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharingcited by 58
  3. 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
  4. 2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
  5. 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
  6. 2022Motley: Benchmarking Heterogeneity and Personalization in Federated Learningcited by 31
  7. 2021Federated f-Differential Privacycited by 29
  8. 2024Fine-Tuning Large Language Models with User-Level Differential Privacycited by 29
  9. 2022Learning Predictions for Algorithms with Predictionscited by 25
  10. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  11. 2022Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learningcited by 23
  12. 2022Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clientscited by 20
29 more
  1. 2021Learning-to-learn non-convex piecewise-Lipschitz functionscited by 15
  2. 2021Efficient Federated Meta-Learning over Multi-Access Wireless Networkscited by 13
  3. 2021Federated Few-Shot Learning with Adversarial Learningcited by 11
  4. 2021Private Multi-Task Learning: Formulation and Applications to Federated Learningcited by 11
  5. 2022Federated learning: Applications, challenges and future directionscited by 11
  6. 2024A Survey on Intelligent Internet of Things: Applications, Security, Privacy, and Future Directionscited by 10
  7. 2021FL-Market: Trading Private Models in Federated Learningcited by 9
  8. 2023Mnemosyne: Learning to Train Transformers with Transformerscited by 9
  9. 2021FedPower: Privacy-Preserving Distributed Eigenspace Estimationcited by 4
  10. 2023Holistic Survey of Privacy and Fairness in Machine Learningcited by 4
  11. 2021PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacycited by 3
  12. 2022Transfer Learning In Differential Privacy's Hybrid-Modelcited by 3
  13. 2023Multi-Task Differential Privacy Under Distribution Skewcited by 3
  14. 2023Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMMcited by 3
  15. 2024ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitationcited by 3
  16. 2021On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Timescited by 2
  17. 2022A Generative Framework for Personalized Learning and Estimation: Theory, Algorithms, and Privacycited by 2
  18. 2024Noise-Aware Differentially Private Regression via Meta-Learningcited by 2
  19. 2021Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacycited by 1
  20. 2025FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fieldscited by 1
  21. 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacycited by 1
  22. 2022Secure Distributed/Federated Learning: Prediction-Privacy Trade-Off for Multi-Agent Systemcited by 0
  23. 2024Advancing Explainable AI Toward Human-Like Intelligence: Forging the Path to Artificial Braincited by 0
  24. 2024Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learningcited by 0
  25. 2024Towards Robust Federated Analytics via Differentially Private Measurements of Statistical Heterogeneitycited by 0
  26. 2025Adaptive Clipping for Privacy-Preserving Few-Shot Learning: Enhancing Generalization with Limited Datacited by 0
  27. 2025Dyn-D2P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guaranteecited by 0
  28. 2025FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projectioncited by 0
  29. 2026Privacy-Aware Collaborative and Distributed Bayesian Optimizationcited by 0