Federated Adversarial Domain Adaptation

Abstract

Federated learning improves data privacy and efficiency in machine learning performed over networks of distributed devices, such as mobile phones, IoT and wearable devices, etc. Yet models trained with federated learning can still fail to generalize to new devices due to the problem of domain shift. Domain shift occurs when the labeled data collected by source nodes statistically differs from the target node's unlabeled data. In this work, we present a principled approach to the problem of federated domain adaptation, which aims to align the representations learned among the different nodes with the data distribution of the target node. Our approach extends adversarial adaptation techniques to the constraints of the federated setting. In addition, we devise a dynamic attention mechanism and leverage feature disentanglement to enhance knowledge transfer. Empirically, we perform extensive experiments on several image and text classification tasks and show promising results under unsupervised federated domain adaptation setting.

Published as a conference paper at ICLR 2020

References in corpus (13)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Semi-Supervised Learning with Deep Generative Models
• Conditional Adversarial Domain Adaptation
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Secure Federated Transfer Learning
• Revisiting Batch Normalization For Practical Domain Adaptation
• Disentangling factors of variation in deep representations using adversarial training
• Domain Agnostic Learning with Disentangled Representations
• A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
• Moment Matching for Multi-Source Domain Adaptation

Cited by in corpus (29)

• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• Robust Federated Learning with Noisy Labels
• Memory-aware curriculum federated learning for breast cancer classification
• Federated Learning on Non-IID Data Silos: An Experimental Study
• Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospective
• Oort: Efficient Federated Learning via Guided Participant Selection
• KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
• FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space
• Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability
• Auto-weighted Robust Federated Learning with Corrupted Data Sources
• Federated Continual Learning: Concepts, Challenges, and Solutions
• Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
• FedH2L: Federated Learning with Model and Statistical Heterogeneity
• Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models
• Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning
• Applications of Federated Learning in Smart Cities: Recent Advances, Taxonomy, and Open Challenges
• Federated Learning -- Methods, Applications and beyond
• Federated Learning on Non-IID Data: A Survey
• Style Normalization and Restitution for Domain Generalization and Adaptation
• Voting-based Approaches For Differentially Private Federated Learning
• Addressing Class Imbalance in Federated Learning
• Decentralised Person Re-Identification with Selective Knowledge Aggregation
• Preliminary Steps Towards Federated Sentiment Classification
• Algorithm Fairness in AI for Medicine and Healthcare
• Client Adaptation improves Federated Learning with Simulated Non-IID Clients
• Collaborative Semantic Aggregation and Calibration for Federated Domain Generalization
• FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation