Private Federated Learning with Domain Adaptation

By Daniel W. Peterson, Pallika H. Kanani, Virendra J. Marathe. 2019

91 citations recorded by the source corpus.

Federated Learning (FL) is a distributed machine learning (ML) paradigm that enables multiple parties to jointly re-train a shared model without sharing their data with any other parties, offering advantages in both scale and privacy. We propose a framework to augment this collaborative model-building with per-user domain adaptation. We show that this technique improves model accuracy for all users, using both real and synthetic data, and that this improvement is much more pronounced when differential privacy bounds are imposed on the FL model.

Subfields: Artificial Intelligence, Computer Science Applications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Science Applications

Citations in the corpus

Salvaging Federated Learning by Local Adaptation (2020, background): “…of privacy and integrity protections on individual participants’ accuracy, and (c) purely local adaptation techniques other than ﬁne-tuning (the only exception is a short paper (Peterson et al., 2019) that uses domain adaptation to counteract the reduction in accuracy due to differential privacy).”
Personalized Federated Learning with First Order Model Optimization (2020, methodology): “Our method strongly outperforms other methods in non-IID federated learning settings.”
Lower Bounds and Optimal Algorithms for Personalized Federated Learning (2020, background): “There are multiple strategies in the literature for incorporating e personalization into FL: multi-task learning [49, 48, 14], transfer learning [54, 23], variational inference [8], mixing of local and global models [41, 19, 31, 10] and others [13].”
Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, unknown): “In [159], the authors propose a privacy-preserving”
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning (2022, background): “There exist extensive works on improving the global performance of FL via client selection [4, 7, 15], split learning [11, 38], domain adaptation [26, 33], etc.”
Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results (2020, methodology): “Federated domain adaptation has been recently proposed [29], [30].”