mlsanityData to 7 Oct 2026

Gains: Fine-grained Federated Domain Adaptation in Open Set

arXiv 2510.15967 ↗First posted 12 Oct 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Conventional federated learning (FL) assumes a closed world with a fixed total number of clients. In contrast, new clients continuously join the FL process in real-world scenarios, introducing new knowledge. This raises two critical demands: detecting new knowledge, i.e., knowledge discovery, and integrating it into the global model, i.e., knowledge adaptation. Existing research focuses on coarse-grained knowledge discovery, and often sacrifices source domain performance and adaptation efficiency. To this end, we propose a fine-grained federated domain adaptation approach in open set (Gains). Gains splits the model into an encoder and a classifier, empirically revealing features extracted by the encoder are sensitive to domain shifts while classifier parameters are sensitive to class increments. Based on this, we develop fine-grained knowledge discovery and contribution-driven aggregation techniques to identify and incorporate new knowledge. Additionally, an anti-forgetting mechanism is designed to preserve source domain performance, ensuring balanced adaptation. Experimental results on multi-domain datasets across three typical data-shift scenarios demonstrate that Gains significantly outperforms other baselines in performance for both source-domain and target-domain clients. Code is available at: https://github.com/Zhong-Zhengyi/Gains.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 67 references that are in the map. First posted on arXiv 12 Oct 2025.

Builds on

33 of 67 references.

References · 33

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  3. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  4. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  5. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  6. 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
  7. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  8. 2022Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptationcited by 66
  9. 2022Federated Domain Generalization for Image Recognition via Cross-Client Style Transfercited by 40
  10. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  11. 2022Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learningcited by 35
  12. 2020Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variablescited by 33
21 more
  1. 2024Towards Efficient Replay in Federated Incremental Learningcited by 33
  2. 2024Domain Generalization through Meta-Learning: A Surveycited by 28
  3. 2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 28
  4. 2023Federated Domain Generalization: A Surveycited by 25
  5. 2024Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matchingcited by 21
  6. 2024Personalized Federated Continual Learning via Multi-granularity Promptcited by 20
  7. 2025Model Predictive Task Sampling for Efficient and Robust Adaptationcited by 20
  8. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  9. 2021Collaborative Semantic Aggregation and Calibration for Federated Domain Generalizationcited by 16
  10. 2025Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adaptercited by 15
  11. 2025Structural features of the fly olfactory circuit mitigate the stability-plasticity dilemma in continual learningcited by 14
  12. 2023Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Trainingcited by 12
  13. 2024Robust Fast Adaptation from Adversarially Explicit Task Distribution Generationcited by 12
  14. 2021Privacy-Preserving Constrained Domain Generalization via Gradient Alignmentcited by 8
  15. 2025SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devicescited by 8
  16. 2023Principled Federated Domain Adaptation: Gradient Projection and Auto-Weightingcited by 6
  17. 2024Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuningcited by 6
  18. 2022StatMix: Data augmentation method that relies on image statistics in federated learningcited by 4
  19. 2024Feature Diversification and Adaptation for Federated Domain Generalizationcited by 4
  20. 2025FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillationcited by 4
  21. 2024SiamSeg: Self-Training with Contrastive Learning for Unsupervised Domain Adaptation Semantic Segmentation in Remote Sensingcited by 3

Built on by

Not cited yet.