Federated Domain Adaptation

Federated domain adaptation tackles the challenge of adapting machine learning models trained on multiple, private datasets (source domains) to a new, different dataset (target domain) without directly sharing sensitive data. Current research focuses on developing decentralized algorithms, often employing optimal transport, generative adversarial networks, or contrastive learning, to align data distributions across domains and improve model generalization. This approach is crucial for addressing privacy concerns in various applications, such as medical imaging, autonomous vehicles, and recommendation systems, where data is distributed and sensitive. The resulting advancements enhance model robustness and efficiency in diverse real-world scenarios while respecting data privacy.

Papers

October 10, 2024

Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning
Jingyuan Zhang, Yiyang Duan, Shuaicheng Niu, Yang Cao, Wei Yang Bryan Lim
Fine Tuning Multi Domain Domain Performance Federated Domain Adaptation Feature Space Hijacking Attack

July 16, 2024

Dataset Dictionary Learning in a Wasserstein Space for Federated Domain Adaptation
Eduardo Fernandes Montesuma, Fabiola Espinoza Castellon, Fred Ngolè Mboula, Aurélien Mayoue, Antoine Souloumiac, Cédric Gouy-Pailler
Multi Source Domain Adaptation Wasserstein Space Federated Domain Adaptation Dataset Dictionary Learning

April 26, 2024

Federated Transfer Component Analysis Towards Effective VNF Profiling
Xunzheng Zhang, Shadi Moazzeni, Juan Marcelo Parra-Ullauri, Reza Nejabati, Dimitra Simeonidou
Generative Adversarial Network Principal Component Analysis Federated Domain Adaptation

April 9, 2024

Collaborative Multi-source Domain Adaptation Through Optimal Transport
Omar Ghannou, Younès Bennani
Domain Adaptation Optimal Transport Source Domain Unlabeled Target Domain Multi Source Domain Adaptation Federated Domain Adaptation

March 20, 2024

When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather
Giulia Rizzoli, Matteo Caligiuri, Donald Shenaj, Francesco Barbato, Pietro Zanuttigh
Semantic Segmentation Various Fast Moving Drone Source Free Domain Adaptation Adverse Weather Main CAR Sale Factor Federated Domain Adaptation Hyperbolic Learning

January 2, 2024

Unsupervised Federated Domain Adaptation for Segmentation of MRI Images
Navapat Nananukul, Hamid Soltanian-zadeh, Mohammad Rostami
Semantic Segmentation Domain Adaptation Segmentation Based Approach Magnetic Resonance Image Unlabeled Target Domain Federated Domain Adaptation Domain Annotation

November 27, 2023

UFDA: Universal Federated Domain Adaptation with Practical Assumptions
Xinhui Liu, Zhenghao Chen, Luping Zhou, Dong Xu, Wei Xi, Gairui Bai, Yihan Zhao, Jizhong Zhao
Modeling Assumption Federated Domain Adaptation DOmain Label Label Disambiguation

November 8, 2023

Robust and Communication-Efficient Federated Domain Adaptation via Random Features
Zhanbo Feng, Yuanjie Wang, Jie Li, Fan Yang, Jiong Lou, Tiebin Mi, Robert. C. Qiu, Zhenyu Liao
Domain Adaptation Machine Learning Model Domain Shift Random Feature Federated Domain Adaptation

July 12, 2023

FDAPT: Federated Domain-adaptive Pre-training for Language Models
Lekang Jiang, Filip Svoboda, Nicholas D. Lane
Language Model Foundation Model Federated Prompt Cooperation Domain Adaptive Federated Domain Adaptation

June 5, 2023

Personalized Federated Domain Adaptation for Item-to-Item Recommendation
Ziwei Fan, Hao Ding, Anoop Deoras, Trong Nghia Hoang
Effective Recommendation Recommendation System Graph Based Graph Domain Adaptation Heterogeneous User Federated Domain Adaptation

May 7, 2023

Model-Contrastive Federated Domain Adaptation
Chang'an Yi, Haotian Chen, Yonghui Xu, Yifan Zhang
Convolutional Neural Network Contrastive Learning Cross Domain Transferable Representation Federated Domain Adaptation

April 24, 2023

Multi-Source to Multi-Target Decentralized Federated Domain Adaptation
Su Wang, Seyyedali Hosseinalipour, Christopher G. Brinton
Domain Adaptation Machine Learning Model Generalization Error Federated Domain Adaptation Source Target

February 10, 2023

Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
Enyi Jiang, Yibo Jacky Zhang, Sanmi Koyejo
Domain Shift Aggregation Method Gradient Projection Federated Stochastic Federated Domain Adaptation Linear Weighting Server Side Aggregation

July 21, 2022

Federated Semi-Supervised Domain Adaptation via Knowledge Transfer
Madhureeta Das, Xianhao Chen, Xiaoyong Yuan, Lan Zhang
Knowledge Distillation Knowledge Transfer Semi Supervised Domain Adaptation Federated Domain Adaptation

April 9, 2022

Federated Unsupervised Domain Adaptation for Face Recognition
Weiming Zhuang, Xin Gan, Yonggang Wen, Xuesen Zhang, Shuai Zhang, Shuai Yi
Domain Adaptation Unsupervised Domain Adaptation Face Recognition Federated Domain Adaptation

March 30, 2022

Federated Domain Adaptation for ASR with Full Self-Supervision
Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli, Frank Seide
Automatic Speech Recognition Self Supervision ASR Model RNN Transducer Audio Domain Federated Domain Adaptation Device Automatic Speech Recognition

November 22, 2021

Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability
Yan Kang, Yang Liu, Yuezhou Wu, Guoqiang Ma, Qiang Yang
Domain Adaptation Inherent Interpretability Adversarial Domain Adaptation Domain Discriminator Federated Domain Adaptation