paper-with-me

Papers

Private Domain Adaptation from a Public Source

2022-08-12 · Raef Bassily, Mehryar Mohri, Ananda Theertha Suresh

A key problem in a variety of applications is that of domain adaptation from a public source domain, for which a relatively large amount of labeled data with no privacy constraints is at one's disposal, to a private target domain, for which a private sample is available with very few or no labeled data. In regression problems with no privacy constraints on the source or target data, a discrepancy minimization algorithm based on several theoretical guarantees was shown to outperform a number of other adaptation algorithm baselines. Building on that approach, we design differentially private discrepancy-based algorithms for adaptation from a source domain with public labeled data to a target domain with unlabeled private data. The design and analysis of our private algorithms critically hinge upon several key properties we prove for a smooth approximation of the weighted discrepancy, such as its smoothness with respect to the $\ell_1$-norm and the sensitivity of its gradient. Our solutions are based on private variants of Frank-Wolfe and Mirror-Descent algorithms. We show that our adaptation algorithms benefit from strong generalization and privacy guarantees and report the results of experiments demonstrating their effectiveness.

📄 PDF Abstract BibTeX arXiv:2208.06135

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Similar Papers 제목 키워드 기반

Differentially Private Domain Adaptation with Theoretical Guarantees

2023-06-15 · Raef Bassily, Corinna Cortes, Anqi Mao, Mehryar Mohri

In many applications, the labeled data at the learner's disposal is subject to privacy constraints and is relatively limited. To derive a more accurate predictor for the target domain, it is often beneficial to leverage …

Domain Adaptation

Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach

2018-10-26 · ICLR 2019 5 · Behnam Gholami, Pritish Sahu, Ognjen Rudovic, Konstantinos Bousmalis 외

Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain. However, in many real-world settings one seeks to adapt to multiple, …

DisentanglementDomain AdaptationMulti-target Domain AdaptationUnsupervised Domain Adaptation

Associative Partial Domain Adaptation

2020-08-07 · Youngeun Kim, Sungeun Hong, Seunghan Yang, Sungil Kang 외

Partial Adaptation (PDA) addresses a practical scenario in which the target domain contains only a subset of classes in the source domain. While PDA should take into account both class-level and sample-level to mitigate …

Domain AdaptationPartial Domain Adaptation

Universal Domain Adaptation for Semantic Segmentation

2025-01-01 · CVPR 2025 1 · Seun-An Choe, Keon-Hee Park, Jinwoo Choi, Gyeong-Moon Park

Unsupervised domain adaptation for semantic segmentation (UDA-SS) aims to transfer knowledge from labeled synthetic data (source) to unlabeled real-world data (target). Traditional UDA-SS methods work on the assumpti…

Domain AdaptationPseudo LabelSemantic SegmentationUniversal Domain Adaptation+1

Active Universal Domain Adaptation

2021-01-01 · ICCV 2021 10 · Xinhong Ma, Junyu Gao, Changsheng Xu

Most unsupervised domain adaptation methods rely on rich prior knowledge about the source-target label set relationship, and they cannot recognize categories beyond the source classes, which limits their applicabilit…

Active LearningDomain AdaptationUniversal Domain AdaptationUnsupervised Domain Adaptation