DeFed-GMM-DaDiL: A Decentralized Federated Framework for Domain Adaptation

• URL: http://arxiv.org/abs/2605.04324v1
• Date: Tue, 05 May 2026 22:00:35 GMT
• Title: DeFed-GMM-DaDiL: A Decentralized Federated Framework for Domain Adaptation
• Abstract summary: DeFed-GMM-DaDiL is an extension of the GMM-Dataset Dictionary Learning (DaDiL) framework.<n>Each client models its dataset as a Gaussian Mixture Model (GMM)<n>We empirically study the stability of the learned representations in scenarios where the target domain has missing classes.
• Score: 7.916373508978821
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decentralized multi-source domain adaptation seeks to transfer knowledge from multiple heterogeneous and related source domains to an unlabeled target domain in a decentralized setting. We address this challenge through a fully decentralized federated approach, DeFed-GMM-DaDiL, an extension of the GMM-Dataset Dictionary Learning (DaDiL) framework. Each client models its dataset as a Gaussian Mixture Model (GMM), and the federation jointly approximates them via labeled Wasserstein barycenters of shared, learnable GMM atoms. This design enables adaptation without a central server while preserving clients' privacy. We empirically study the stability of the learned representations in scenarios where the target domain has missing classes. Empirical results demonstrate that DeFed-GMM-DaDiL maintains stable and consistent shared representations across clients, effectively reconstructs missing classes, and achieves competitive performance on multi-source domain adaptation benchmarks.

Related papers

• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  We argue that replacing parameters with preferences represents a more scalable and privacy-preserving future.<n>We propose MoR, a federated alignment framework based on GRPO with Mixture-of-Rewards for heterogeneous VLMs.<n>MoR consistently outperforms federated alignment baselines in generalization, robustness, and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-01-31T03:11:51Z)
• GMM-COMET: Continual Source-Free Universal Domain Adaptation via a Mean Teacher and Gaussian Mixture Model-Based Pseudo-Labeling [3.1744658275045103]
  Unsupervised domain adaptation tackles the problem that domain shifts between training and test data impair the performance of neural networks in real-world applications.<n>This setting, known as source-free universal domain adaptation (SF-UniDA), has recently gained attention.<n>We present the first study on continual SF-UniDA, where the model must adapt sequentially to a stream of multiple different unlabeled target domains.
  arXiv  Detail & Related papers  (2026-01-16T10:23:19Z)
• FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling [52.05684032172943]
  We propose FedBook, a unified graph foundation codebook that aggregates clients' local codebooks during server-side federated pre-training.<n>FedBook consistently outperforms 21 baselines, including isolated supervised learning, FL/FGL, federated adaptations of centralized GFMs, and FedGFM techniques.
  arXiv  Detail & Related papers  (2025-10-09T03:50:30Z)
• Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models [9.432150710329609]
  Federated Learning (FL) offers a framework for training models collaboratively while preserving data privacy of each client.<n>We propose replacing the FFREEDA backbone with a frozen vision foundation model (VFM)<n>VFMs effectively mitigate the effects of domain gaps, class imbalances, and even non-IID-ness among target clients.
  arXiv  Detail & Related papers  (2025-09-10T08:10:57Z)
• Decentralized Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation [5.042313273982193]
  Decentralized Multi-Source Domain Adaptation (DMSDA) is a challenging task.<n>Our work tackles DMSDA through a fully decentralized federated approach.
  arXiv  Detail & Related papers  (2025-03-22T07:48:48Z)
• 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)
• Federated Learning with Domain Generalization [11.92860245410696]
  Federated Learning enables a group of clients to jointly train a machine learning model with the help of a centralized server. In practice, the model trained over multiple source domains may have poor generalization performance on unseen target domains. We propose FedADG to equip federated learning with domain generalization capability.
  arXiv  Detail & Related papers  (2021-11-20T01:02:36Z)
• 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)
• Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation [102.42638795864178]
  We propose a principled meta-learning based approach to OCDA for semantic segmentation. We cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner. A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code. We learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization.
  arXiv  Detail & Related papers  (2020-12-15T13:21:54Z)
• Mutual Learning Network for Multi-Source Domain Adaptation [73.25974539191553]
  We propose a novel multi-source domain adaptation method, Mutual Learning Network for Multiple Source Domain Adaptation (ML-MSDA) Under the framework of mutual learning, the proposed method pairs the target domain with each single source domain to train a conditional adversarial domain adaptation network as a branch network. The proposed method outperforms the comparison methods and achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-03-29T04:31:43Z)

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.