mlsanityData to 14 Oct 2026

CRIP: Channel Level Representation Injection for Personalized One-Shot Federated Learning

arXiv 2608.02222 ↗First posted 3 Aug 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

One-shot federated learning (OSFL) has emerged as a promising collaborative model learning framework with only a single round of communication, offering significant advantages in communication efficiency and privacy preservation. However, OSFL often faces inherent limitations under severe domain heterogeneity across clients due to the lack of iterative knowledge exchange. Most existing OSFL methods require an auxiliary public dataset for knowledge distillation or leverage statistical information for parameter-level aggregation, overlooking feature shift caused by domain heterogeneity. To address these challenges, we propose CRIP, a personalized OSFL framework that operates in the representation space via channel-level feature alignment. To achieve this, each client uploads its feature extractor to the server, which broadcasts all extractors back to every client. Since not all source clients share compatible feature distributions with the target client, indiscriminate fusion of cross-client features would introduce domain-specific noise. Therefore, CRIP effectively measures the channel-wise representational similarity between the target client and each source client on a small local mini-batch, and selectively fuses only the most compatible features. Extensive experiments on domain-heterogeneous benchmarks such as DomainNet, PACS, and Office-Home demonstrate that CRIP consistently outperforms local models and state-of-the-art baselines, validating the effectiveness of representation-space personalization under extreme domain heterogeneity.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 39 references that are in the map. First posted on arXiv 3 Aug 2026.

Builds on

28 of 39 references.

References · 28

  1. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  2. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  3. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  4. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  5. 2020Distilled One-Shot Federated Learningcited by 109
  6. 2021DENSE: Data-Free One-Shot Federated Learningcited by 100
  7. 2020XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learningcited by 58
  8. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
  9. 2022FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Datacited by 50
  10. 2022Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environmentscited by 49
  11. 2021Fed2: Feature-Aligned Federated Learningcited by 42
  12. 2022FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learningcited by 27
16 more
  1. 2024Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boostingcited by 27
  2. 2022FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentationcited by 24
  3. 2019One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Themcited by 23
  4. 2023Federated Generative Learning with Foundation Modelscited by 23
  5. 2023FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregationcited by 22
  6. 2023GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learningcited by 18
  7. 2024FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Modelscited by 17
  8. 2024FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Modelscited by 16
  9. 2024FedFisher: Leveraging Fisher Information for One-Shot Federated Learningcited by 15
  10. 2024Parametric Feature Transfer: One-shot Federated Learning with Foundation Modelscited by 13
  11. 2024Revisiting Ensembling in One-Shot Federated Learningcited by 13
  12. 2024One-shot Federated Learning via Synthetic Distiller-Distillate Communicationcited by 12
  13. 2024FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusioncited by 11
  14. 2025Capture Global Feature Statistics for One-Shot Federated Learningcited by 6
  15. 2024pFedAFM: Adaptive Feature Mixture for Batch-Level Personalization in Heterogeneous Federated Learningcited by 3
  16. 2025FedBEns: One-Shot Federated Learning based on Bayesian Ensemblecited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models
  2. 2026Feature-Aware One-Shot Federated Learning via Hierarchical Token Sequences
  3. 2026FedBiCross: Personalized One-Shot Federated Learning on Medical Images
  4. 2025FedeCouple: Fine-Grained Balancing of Global-Generalization and Local-Adaptability in Federated Learning
  5. 2023One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models
  6. 2025Co-LoRA: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients
  7. 2023UPFL: Unsupervised Personalized Federated Learning towards New Clients
  8. 2022One-shot Federated Learning without Server-side Training