Gains: Fine-grained Federated Domain Adaptation in Open Set

2025/10/12 by Zhengyi Zhong, Zhong, Zhengyi, Weidong Bao +12
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2510.15967

openalex publication_date 2025/10/12 · openalex created_date 2025/10/22 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices
• Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter
• Ten Challenging Problems in Federated Foundation Models
• Structural features of the fly olfactory circuit mitigate the stability-plasticity dilemma in continual learning
• FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation
• Model Predictive Task Sampling for Efficient and Robust Adaptation
• SiamSeg: Self-Training with Contrastive Learning for Unsupervised Domain Adaptation Semantic Segmentation in Remote Sensing
• Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning
• Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
• Feature Diversification and Adaptation for Federated Domain Generalization
• Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching
• Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity
• Domain Generalization through Meta-Learning: A Survey
• Towards Efficient Replay in Federated Incremental Learning
• Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training
• Federated Domain Generalization: A Survey
• A Comprehensive Survey on Source-free Domain Adaptation
• A Comprehensive Survey on Source-Free Domain Adaptation
• Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
• Recent Advances on Federated Learning: A Systematic Survey
• Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
• Federated Domain Generalization for Image Recognition via Cross-Client Style Transfer
• StatMix: Data augmentation method that relies on image statistics in federated learning
• Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation
• Collaborative Semantic Aggregation and Calibration for Federated Domain Generalization
• Privacy-Preserving Constrained Domain Generalization via Gradient Alignment
• FedProto: Federated Prototype Learning across Heterogeneous Clients
• Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables
• On the Convergence of FedAvg on Non-IID Data
• Transferrable Prototypical Networks for Unsupervised Domain Adaptation
• Federated Optimization in Heterogeneous Networks
• Representation Learning: A Review and New Perspectives
• Representation Learning: A Review and New Perspectives

Related

• Feature Distribution Matching for Federated Domain Generalization
• FedSDAF: Leveraging Source Domain Awareness for Enhanced Federated Domain Generalization
• Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models
• Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning
• Feature Diversification and Adaptation for Federated Domain Generalization