Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization

• URL: http://arxiv.org/abs/2401.10272v1
• Date: Fri, 5 Jan 2024 01:21:37 GMT
• Title: Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization
• Authors: Yikang Wei and Yahong Han
• Abstract summary: Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain. We propose a Multi-source Collaborative Gradient Discrepancy Minimization (MCGDM) method for federated domain generalization.
• Score: 27.171533040583117
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Domain Generalization aims to learn a domain-invariant model from multiple decentralized source domains for deployment on unseen target domain. Due to privacy concerns, the data from different source domains are kept isolated, which poses challenges in bridging the domain gap. To address this issue, we propose a Multi-source Collaborative Gradient Discrepancy Minimization (MCGDM) method for federated domain generalization. Specifically, we propose intra-domain gradient matching between the original images and augmented images to avoid overfitting the domain-specific information within isolated domains. Additionally, we propose inter-domain gradient matching with the collaboration of other domains, which can further reduce the domain shift across decentralized domains. Combining intra-domain and inter-domain gradient matching, our method enables the learned model to generalize well on unseen domains. Furthermore, our method can be extended to the federated domain adaptation task by fine-tuning the target model on the pseudo-labeled target domain. The extensive experiments on federated domain generalization and adaptation indicate that our method outperforms the state-of-the-art methods significantly.

Related papers

• Meta-causal Learning for Single Domain Generalization [102.53303707563612]
  Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains) Existing methods focus on expanding the distribution of the training domain to cover the target domains, but without estimating the domain shift between the source and target domains. We propose a new learning paradigm, namely simulate-analyze-reduce, which first simulates the domain shift by building an auxiliary domain as the target domain, then learns to analyze the causes of domain shift, and finally learns to reduce the domain shift for model adaptation.
  arXiv  Detail & Related papers  (2023-04-07T15:46:38Z)
• ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation [78.19743899703052]
  Open compound domain adaptation (OCDA) considers the target domain as the compound of multiple unknown homogeneous. We introduce a multi-teacher framework with bidirectional photometric mixing to adapt to every target subdomain. We conduct an adaptive distillation to learn a student model and apply consistency regularization to improve the student generalization.
  arXiv  Detail & Related papers  (2022-07-19T03:30:48Z)
• Domain Generalization via Selective Consistency Regularization for Time Series Classification [16.338176636365752]
  Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains. We propose a novel representation learning methodology that selectively enforces prediction consistency between source domains.
  arXiv  Detail & Related papers  (2022-06-16T01:57:35Z)
• Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains [63.23373987549485]
  Cross-domain person re-identification (re-ID) aims to transfer the identity-discriminative knowledge from the source to the target domain. We propose an Intermediate Domain Module (IDM) and a Mirrors Generation Module (MGM) IDM generates multiple intermediate domains by mixing the hidden-layer features from source and target domains. MGM is introduced by mapping the features into the IDM-generated intermediate domains without changing their original identity.
  arXiv  Detail & Related papers  (2022-03-03T12:44:56Z)
• Exploiting Domain-Specific Features to Enhance Domain Generalization [10.774902700296249]
  Domain Generalization (DG) aims to train a model, from multiple observed source domains, in order to perform well on unseen target domains. Prior DG approaches have focused on extracting domain-invariant information across sources to generalize on target domains. We propose meta-Domain Specific-Domain Invariant (mD) - a novel theoretically sound framework.
  arXiv  Detail & Related papers  (2021-10-18T15:42:39Z)
• IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID [58.46907388691056]
  We argue that the bridging between the source and target domains can be utilized to tackle the UDA re-ID task. We propose an Intermediate Domain Module (IDM) to generate intermediate domains' representations on-the-fly. Our proposed method outperforms the state-of-the-arts by a large margin in all the common UDA re-ID tasks.
  arXiv  Detail & Related papers  (2021-08-05T07:19:46Z)
• Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification [57.92800886719651]
  Deep learning-based multi-source unsupervised domain adaptation (MUDA) has been actively studied in recent years. domain shift in MUDA exists not only between the source and target domains but also among multiple source domains. We propose an end-to-end trainable network that exploits domain Consistency Regularization for unsupervised Multi-source domain Adaptive classification.
  arXiv  Detail & Related papers  (2021-06-16T07:29:27Z)
• Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation [74.3349233035632]
  Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) do not consider an inter-class variation within the target domain itself or estimated category. We introduce a learnable clustering module, and a novel domain adaptation framework called cross-domain grouping and alignment. Our method consistently boosts the adaptation performance in semantic segmentation, outperforming the state-of-the-arts on various domain adaptation settings.
  arXiv  Detail & Related papers  (2020-12-15T11:36:21Z)
• Discrepancy Minimization in Domain Generalization with Generative Nearest Neighbors [13.047289562445242]
  Domain generalization (DG) deals with the problem of domain shift where a machine learning model trained on multiple-source domains fail to generalize well on a target domain with different statistics. Multiple approaches have been proposed to solve the problem of domain generalization by learning domain invariant representations across the source domains that fail to guarantee generalization on the shifted target domain. We propose a Generative Nearest Neighbor based Discrepancy Minimization (GNNDM) method which provides a theoretical guarantee that is upper bounded by the error in the labeling process of the target.
  arXiv  Detail & Related papers  (2020-07-28T14:54:25Z)
• Unsupervised Domain Adaptation with Progressive Domain Augmentation [34.887690018011675]
  We propose a novel unsupervised domain adaptation method based on progressive domain augmentation. The proposed method generates virtual intermediate domains via domain, progressively augments the source domain and bridges the source-target domain divergence. We conduct experiments on multiple domain adaptation tasks and the results shows the proposed method achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-04-03T18:45:39Z)

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.