CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift

• URL: http://arxiv.org/abs/2305.18458v2
• Date: Sun, 29 Dec 2024 21:24:30 GMT
• Title: CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift
• Authors: Anh T Nguyen, Lam Tran, Anh Tong, Tuan-Duy H. Nguyen, Toan Tran,
• Abstract summary: Unsupervised domain adaptation (UDA) refers to a domain adaptation framework in which a learning model is trained based on the labeled samples on the source domain and unlabeled ones in the target domain. We propose a novel Conditional Adversarial SUpport ALignment (CASUAL) whose aim is to minimize the conditional symmetric support divergence between the source's and target domain's feature representation distributions.
• Score: 9.2929174544214
• License:
• Abstract: Unsupervised domain adaptation (UDA) refers to a domain adaptation framework in which a learning model is trained based on the labeled samples on the source domain and unlabeled ones in the target domain. The dominant existing methods in the field that rely on the classical covariate shift assumption to learn domain-invariant feature representation have yielded suboptimal performance under label distribution shift. In this paper, we propose a novel Conditional Adversarial SUpport ALignment (CASUAL) whose aim is to minimize the conditional symmetric support divergence between the source's and target domain's feature representation distributions, aiming at a more discriminative representation for the classification task. We also introduce a novel theoretical target risk bound, which justifies the merits of aligning the supports of conditional feature distributions compared to the existing marginal support alignment approach in the UDA settings. We then provide a complete training process for learning in which the objective optimization functions are precisely based on the proposed target risk bound. Our empirical results demonstrate that CASUAL outperforms other state-of-the-art methods on different UDA benchmark tasks under different label shift conditions.

Related papers

• Multi-Source Unsupervised Domain Adaptation with Prototype Aggregation [8.139534851987364]
  Multi-source domain adaptation (MSDA) plays an important role in industrial model generalization. Recent efforts on MSDA focus on enhancing multi-domain distributional alignment. We propose a prototype aggregation method that models the discrepancy between source and target domains at the class and domain levels.
  arXiv  Detail & Related papers  (2024-12-20T06:44:35Z)
• Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment [87.8301166955305]
  We propose a novel bi-discriminator domain adversarial neural network with class-level gradient alignment. BACG resorts to gradient signals and second-order probability estimation for better alignment of domain distributions. In addition, inspired by contrastive learning, we develop a memory bank-based variant, i.e. Fast-BACG, which can greatly shorten the training process.
  arXiv  Detail & Related papers  (2023-10-21T09:53:17Z)
• Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction [62.41511766918932]
  Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining. Recent work focus on cross-domain OTE, which is typically encountered in real-world scenarios. We propose a new SSL approach that opts for selecting target samples whose model output from a domain-specific teacher and student network disagrees on the unlabelled target data.
  arXiv  Detail & Related papers  (2023-02-28T16:31:17Z)
• Maximizing Conditional Independence for Unsupervised Domain Adaptation [9.533515002375545]
  We study how to transfer a learner from a labeled source domain to an unlabeled target domain with different distributions. In addition to unsupervised domain adaptation, we extend our method to the multi-source scenario in a natural and elegant way.
  arXiv  Detail & Related papers  (2022-03-07T08:59:21Z)
• Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation [74.71931918541748]
  We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA. We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process. We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-03T01:33:14Z)
• Your Classifier can Secretly Suffice Multi-Source Domain Adaptation [72.47706604261992]
  Multi-Source Domain Adaptation (MSDA) deals with the transfer of task knowledge from multiple labeled source domains to an unlabeled target domain. We present a different perspective to MSDA wherein deep models are observed to implicitly align the domains under label supervision.
  arXiv  Detail & Related papers  (2021-03-20T12:44:13Z)
• Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation [116.48885692054724]
  We propose a reinforcement learning based selective pseudo-labeling method for semi-supervised domain adaptation. We develop a deep Q-learning model to select both accurate and representative pseudo-labeled instances. Our proposed method is evaluated on several benchmark datasets for SSDA, and demonstrates superior performance to all the comparison methods.
  arXiv  Detail & Related papers  (2020-12-07T03:37:38Z)
• 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)
• Target Consistency for Domain Adaptation: when Robustness meets Transferability [8.189696720657247]
  Learning Invariant Representations has been successfully applied for reconciling a source and a target domain for Unsupervised Domain Adaptation. We show that the cluster assumption is violated in the target domain despite being maintained in the source domain. Our new approach results in a significant improvement, on both image classification and segmentation benchmarks.
  arXiv  Detail & Related papers  (2020-06-25T09:13:00Z)
• Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation [18.90240379173491]
  Current methods for class-conditioned domain alignment aim to explicitly minimize a loss function based on pseudo-label estimations of the target domain. We propose a method that removes the need for explicit optimization of model parameters from pseudo-labels directly. We present a sampling-based implicit alignment approach, where the sample selection procedure is implicitly guided by the pseudo-labels.
  arXiv  Detail & Related papers  (2020-06-09T00:20:21Z)

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.