Partial Identifiability for Domain Adaptation

• URL: http://arxiv.org/abs/2306.06510v1
• Date: Sat, 10 Jun 2023 19:04:03 GMT
• Title: Partial Identifiability for Domain Adaptation
• Authors: Lingjing Kong, Shaoan Xie, Weiran Yao, Yujia Zheng, Guangyi Chen, Petar Stojanov, Victor Akinwande, Kun Zhang
• Abstract summary: We propose a practical domain adaptation framework called iMSDA. We show that iMSDA outperforms state-of-the-art domain adaptation algorithms on benchmark datasets.
• Score: 17.347755928718872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unsupervised domain adaptation is critical to many real-world applications where label information is unavailable in the target domain. In general, without further assumptions, the joint distribution of the features and the label is not identifiable in the target domain. To address this issue, we rely on the property of minimal changes of causal mechanisms across domains to minimize unnecessary influences of distribution shifts. To encode this property, we first formulate the data-generating process using a latent variable model with two partitioned latent subspaces: invariant components whose distributions stay the same across domains and sparse changing components that vary across domains. We further constrain the domain shift to have a restrictive influence on the changing components. Under mild conditions, we show that the latent variables are partially identifiable, from which it follows that the joint distribution of data and labels in the target domain is also identifiable. Given the theoretical insights, we propose a practical domain adaptation framework called iMSDA. Extensive experimental results reveal that iMSDA outperforms state-of-the-art domain adaptation algorithms on benchmark datasets, demonstrating the effectiveness of our framework.

Related papers

• Subspace Identification for Multi-Source Domain Adaptation [30.98339926222619]
  Multi-source domain adaptation (MSDA) methods aim to transfer knowledge from multiple labeled source domains to an unlabeled target domain. Current methods require an adequate number of domains, monotonic transformation of latent variables, and invariant label distributions. We propose a subspace identification theory that guarantees the disentanglement of domain-invariant and domain-specific variables.
  arXiv  Detail & Related papers  (2023-10-07T07:52:59Z)
• Identifiable Latent Causal Content for Domain Adaptation under Latent Covariate Shift [82.14087963690561]
  Multi-source domain adaptation (MSDA) addresses the challenge of learning a label prediction function for an unlabeled target domain. We present an intricate causal generative model by introducing latent noises across domains, along with a latent content variable and a latent style variable. The proposed approach showcases exceptional performance and efficacy on both simulated and real-world datasets.
  arXiv  Detail & Related papers  (2022-08-30T11:25:15Z)
• Discovering Domain Disentanglement for Generalized Multi-source Domain Adaptation [48.02978226737235]
  A typical multi-source domain adaptation (MSDA) approach aims to transfer knowledge learned from a set of labeled source domains, to an unlabeled target domain. We propose a variational domain disentanglement (VDD) framework, which decomposes the domain representations and semantic features for each instance by encouraging dimension-wise independence.
  arXiv  Detail & Related papers  (2022-07-11T04:33:08Z)
• Controlled Generation of Unseen Faults for Partial and OpenSet&Partial Domain Adaptation [0.0]
  New operating conditions can result in a performance drop of fault diagnostics models due to the domain gap between the training and the testing data distributions. We propose a new framework based on a Wasserstein GAN for Partial and OpenSet&Partial domain adaptation. The main contribution is the controlled fault data generation that enables to generate unobserved fault types and severity levels in the target domain.
  arXiv  Detail & Related papers  (2022-04-29T13:05:25Z)
• Domain-Agnostic Prior for Transfer Semantic Segmentation [197.9378107222422]
  Unsupervised domain adaptation (UDA) is an important topic in the computer vision community. We present a mechanism that regularizes cross-domain representation learning with a domain-agnostic prior (DAP) Our research reveals that UDA benefits much from better proxies, possibly from other data modalities.
  arXiv  Detail & Related papers  (2022-04-06T09:13:25Z)
• Self-Adversarial Disentangling for Specific Domain Adaptation [52.1935168534351]
  Domain adaptation aims to bridge the domain shifts between the source and target domains. Recent methods typically do not consider explicit prior knowledge on a specific dimension.
  arXiv  Detail & Related papers  (2021-08-08T02:36:45Z)
• Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification [87.72851934197936]
  Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching. One challenge is how to generate target domain samples with reliable labels for training. We propose a Disentanglement-based Cross-Domain Feature Augmentation strategy.
  arXiv  Detail & Related papers  (2021-03-25T15:28:41Z)
• Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation [66.74638960925854]
  Partial domain adaptation (PDA) deals with a realistic and challenging problem when the source domain label space substitutes the target domain. We propose an Adaptively-Accumulated Knowledge Transfer framework (A$2$KT) to align the relevant categories across two domains.
  arXiv  Detail & Related papers  (2020-08-27T00:53:43Z)
• Domain Adaptation as a Problem of Inference on Graphical Models [46.68286696120191]
  It is unknown in advance how the joint distribution changes across domains. We propose to use a graphical model as a compact way to encode the change property of the joint distribution.
  arXiv  Detail & Related papers  (2020-02-09T04:08:15Z)

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.