Data Collaboration Analysis Over Matrix Manifolds
- URL: http://arxiv.org/abs/2403.02780v1
- Date: Tue, 5 Mar 2024 08:52:16 GMT
- Title: Data Collaboration Analysis Over Matrix Manifolds
- Authors: Keiyu Nosaka, Akiko Yoshise
- Abstract summary: Privacy-Preserving Machine Learning (PPML) addresses this challenge by safeguarding sensitive information.
NRI-DC framework emerges as an innovative approach, potentially resolving the 'data island' issue among institutions.
This study establishes a rigorous theoretical foundation for these collaboration functions and introduces new formulations.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The effectiveness of machine learning (ML) algorithms is deeply intertwined
with the quality and diversity of their training datasets. Improved datasets,
marked by superior quality, enhance the predictive accuracy and broaden the
applicability of models across varied scenarios. Researchers often integrate
data from multiple sources to mitigate biases and limitations of single-source
datasets. However, this extensive data amalgamation raises significant ethical
concerns, particularly regarding user privacy and the risk of unauthorized data
disclosure. Various global legislative frameworks have been established to
address these privacy issues. While crucial for safeguarding privacy, these
regulations can complicate the practical deployment of ML technologies.
Privacy-Preserving Machine Learning (PPML) addresses this challenge by
safeguarding sensitive information, from health records to geolocation data,
while enabling the secure use of this data in developing robust ML models.
Within this realm, the Non-Readily Identifiable Data Collaboration (NRI-DC)
framework emerges as an innovative approach, potentially resolving the 'data
island' issue among institutions through non-iterative communication and robust
privacy protections. However, in its current state, the NRI-DC framework faces
model performance instability due to theoretical unsteadiness in creating
collaboration functions. This study establishes a rigorous theoretical
foundation for these collaboration functions and introduces new formulations
through optimization problems on matrix manifolds and efficient solutions.
Empirical analyses demonstrate that the proposed approach, particularly the
formulation over orthogonal matrix manifolds, significantly enhances
performance, maintaining consistency and efficiency without compromising
communication efficiency or privacy protections.
Related papers
- A Robust Negative Learning Approach to Partial Domain Adaptation Using
Source Prototypes [0.8895157045883034]
This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem.
It includes diverse, complementary label feedback, alleviating the effect of incorrect feedback and promoting pseudo-label refinement.
We conducted a series of comprehensive experiments, including an ablation analysis, covering a range of partial domain adaptation tasks.
arXiv Detail & Related papers (2023-09-07T07:26:27Z) - Divide and Contrast: Source-free Domain Adaptation via Adaptive
Contrastive Learning [122.62311703151215]
Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations.
DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals.
We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
arXiv Detail & Related papers (2022-11-12T09:21:49Z) - Memory Consistent Unsupervised Off-the-Shelf Model Adaptation for
Source-Relaxed Medical Image Segmentation [13.260109561599904]
Unsupervised domain adaptation (UDA) has been a vital protocol for migrating information learned from a labeled source domain to an unlabeled heterogeneous target domain.
We propose "off-the-shelf (OS)" UDA (OSUDA), aimed at image segmentation, by adapting an OS segmentor trained in a source domain to a target domain, in the absence of source domain data in adaptation.
arXiv Detail & Related papers (2022-09-16T13:13:50Z) - On Certifying and Improving Generalization to Unseen Domains [87.00662852876177]
Domain Generalization aims to learn models whose performance remains high on unseen domains encountered at test-time.
It is challenging to evaluate DG algorithms comprehensively using a few benchmark datasets.
We propose a universal certification framework that can efficiently certify the worst-case performance of any DG method.
arXiv Detail & Related papers (2022-06-24T16:29:43Z) - Balancing Discriminability and Transferability for Source-Free Domain
Adaptation [55.143687986324935]
Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations.
The requirement of simultaneous access to labeled source and unlabeled target renders them unsuitable for the challenging source-free DA setting.
We derive novel insights to show that a mixup between original and corresponding translated generic samples enhances the discriminability-transferability trade-off.
arXiv Detail & Related papers (2022-06-16T09:06:22Z) - Source-Free Domain Adaptation via Distribution Estimation [106.48277721860036]
Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different.
Recently, Source-Free Domain Adaptation (SFDA) has drawn much attention, which tries to tackle domain adaptation problem without using source data.
In this work, we propose a novel framework called SFDA-DE to address SFDA task via source Distribution Estimation.
arXiv Detail & Related papers (2022-04-24T12:22:19Z) - Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains.
We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
arXiv Detail & Related papers (2021-12-12T06:11:16Z) - Adapting Off-the-Shelf Source Segmenter for Target Medical Image
Segmentation [12.703234995718372]
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled and unseen target domain.
Access to the source domain data at the adaptation stage is often limited, due to data storage or privacy issues.
We propose to adapt an off-the-shelf" segmentation model pre-trained in the source domain to the target domain.
arXiv Detail & Related papers (2021-06-23T16:16:55Z) - Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain
Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain.
We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one.
Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
arXiv Detail & Related papers (2020-12-08T08:52:00Z) - Unsupervised Domain Adaptation via Structurally Regularized Deep
Clustering [35.008158504090176]
Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data on a target domain, given labeled data on a source domain whose distribution shifts from the target one.
We propose to directly uncover the intrinsic target discrimination via discriminative clustering of target data.
We term our proposed method as Structurally Regularized Deep Clustering (SRDC), where we also enhance target discrimination with clustering of intermediate network features.
arXiv Detail & Related papers (2020-03-19T07:26:41Z)
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.