Discrepancy-Based Active Learning for Domain Adaptation

• URL: http://arxiv.org/abs/2103.03757v1
• Date: Fri, 5 Mar 2021 15:36:48 GMT
• Title: Discrepancy-Based Active Learning for Domain Adaptation
• Authors: Antoine de Mathelin, Mathilde Mougeot, Nicolas Vayatis
• Abstract summary: The goal of the paper is to design active learning strategies which lead to domain adaptation under an assumption of domain shift. We derive bounds for such active learning strategies in terms of Rademacher average and localized discrepancy for general loss functions. We provide improved versions of the algorithms to address the case of large data sets.
• Score: 7.283533791778357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The goal of the paper is to design active learning strategies which lead to domain adaptation under an assumption of domain shift in the case of Lipschitz labeling function. Building on previous work by Mansour et al. (2009) we adapt the concept of discrepancy distance between source and target distributions to restrict the maximization over the hypothesis class to a localized class of functions which are performing accurate labeling on the source domain. We derive generalization error bounds for such active learning strategies in terms of Rademacher average and localized discrepancy for general loss functions which satisfy a regularity condition. Practical algorithms are inferred from the theoretical bounds, one is based on greedy optimization and the other is a K-medoids algorithm. We also provide improved versions of the algorithms to address the case of large data sets. These algorithms are competitive against other state-of-the-art active learning techniques in the context of domain adaptation as shown in our numerical experiments, in particular on large data sets of around one hundred thousand images.

Related papers

• Domain Adversarial Active Learning for Domain Generalization Classification [8.003401798449337]
  Domain generalization models aim to learn cross-domain knowledge from source domain data, to improve performance on unknown target domains. Recent research has demonstrated that diverse and rich source domain samples can enhance domain generalization capability. We propose a domain-adversarial active learning (DAAL) algorithm for classification tasks in domain generalization.
  arXiv  Detail & Related papers  (2024-03-10T10:59:22Z)
• Domain-aware Triplet loss in Domain Generalization [0.0]
  Domain shift is caused by discrepancies in the distributions of the testing and training data. We design a domainaware triplet loss for domain generalization to help the model to cluster similar semantic features. Our algorithm is designed to disperse domain information in the embedding space.
  arXiv  Detail & Related papers  (2023-03-01T14:02:01Z)
• Domain Adaptation via Rebalanced Sub-domain Alignment [22.68115322836635]
  Unsupervised domain adaptation (UDA) is a technique used to transfer knowledge from a labeled source domain to a related unlabeled target domain. Many UDA methods have shown success in the past, but they often assume that the source and target domains must have identical class label distributions. We propose a novel generalization bound that reweights source classification error by aligning source and target sub-domains.
  arXiv  Detail & Related papers  (2023-02-03T21:30:40Z)
• Algorithms and Theory for Supervised Gradual Domain Adaptation [19.42476993856205]
  We study the problem of supervised gradual domain adaptation, where labeled data from shifting distributions are available to the learner along the trajectory. Under this setting, we provide the first generalization upper bound on the learning error under mild assumptions. Our results are algorithm agnostic for a range of loss functions, and only depend linearly on the averaged learning error across the trajectory.
  arXiv  Detail & Related papers  (2022-04-25T13:26:11Z)
• f-Domain-Adversarial Learning: Theory and Algorithms [82.97698406515667]
  Unsupervised domain adaptation is used in many machine learning applications where, during training, a model has access to unlabeled data in the target domain. We derive a novel generalization bound for domain adaptation that exploits a new measure of discrepancy between distributions based on a variational characterization of f-divergences.
  arXiv  Detail & Related papers  (2021-06-21T18:21:09Z)
• Model-Based Domain Generalization [96.84818110323518]
  We propose a novel approach for the domain generalization problem called Model-Based Domain Generalization. Our algorithms beat the current state-of-the-art methods on the very-recently-proposed WILDS benchmark by up to 20 percentage points.
  arXiv  Detail & Related papers  (2021-02-23T00:59:02Z)
• A Theory of Label Propagation for Subpopulation Shift [61.408438422417326]
  We propose a provably effective framework for domain adaptation based on label propagation. We obtain end-to-end finite-sample guarantees on the entire algorithm. We extend our theoretical framework to a more general setting of source-to-target transfer based on a third unlabeled dataset.
  arXiv  Detail & Related papers  (2021-02-22T17:27:47Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)
• Adaptive Risk Minimization: Learning to Adapt to Domain Shift [109.87561509436016]
  A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. In this work, we consider the problem setting of domain generalization, where the training data are structured into domains and there may be multiple test time shifts. We introduce the framework of adaptive risk minimization (ARM), in which models are directly optimized for effective adaptation to shift by learning to adapt on the training domains.
  arXiv  Detail & Related papers  (2020-07-06T17:59:30Z)
• Unsupervised Domain Adaptive Object Detection using Forward-Backward Cyclic Adaptation [13.163271874039191]
  We present a novel approach to perform the unsupervised domain adaptation for object detection through forward-backward cyclic (FBC) training. Recent adversarial training based domain adaptation methods have shown their effectiveness on minimizing domain discrepancy via marginal feature distributions alignment. We propose Forward-Backward Cyclic Adaptation, which iteratively computes adaptation from source to target via backward hopping and from target to source via forward passing.
  arXiv  Detail & Related papers  (2020-02-03T06:24:58Z)
• Domain Adaptation: Learning Bounds and Algorithms [80.85426994513541]
  We introduce a novel distance between distributions, discrepancy distance, that is tailored to adaptation problems with arbitrary loss functions. We derive novel generalization bounds for domain adaptation for a wide family of loss functions. We also present a series of novel adaptation bounds for large classes of regularization-based algorithms.
  arXiv  Detail & Related papers  (2009-02-19T18:42:16Z)

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.