# KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation

arXiv: https://arxiv.org/abs/2011.09757 · HTML: https://mlsanity.com/paper/2011.09757/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 30 of 50)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark](https://mlsanity.com/paper/2311.06750/) (2023)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [DINE: Domain Adaptation from Single and Multiple Black-box Predictors](https://mlsanity.com/paper/2104.01539/) (2021)
- [INTERN: A New Learning Paradigm Towards General Vision](https://mlsanity.com/paper/2111.08687/) (2021)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring](https://mlsanity.com/paper/2206.06818/) (2022)
- [Cross-Domain Ensemble Distillation for Domain Generalization](https://mlsanity.com/paper/2211.14058/) (2022)
- [Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors](https://mlsanity.com/paper/2405.11525/) (2024)
- [GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning](https://mlsanity.com/paper/2308.10279/) (2023)
- [Federated Distillation: A Survey](https://mlsanity.com/paper/2404.08564/) (2024)
- [Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truth](https://mlsanity.com/paper/2406.00474/) (2024)
- [FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection](https://mlsanity.com/paper/2410.11397/) (2024)
- [Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization](https://mlsanity.com/paper/2401.10272/) (2024)
- [FedHarmony: Unlearning Scanner Bias with Distributed Data](https://mlsanity.com/paper/2205.15970/) (2022)
- [More is Better: Deep Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2405.00749/) (2024)
- [Influence-Oriented Personalized Federated Learning](https://mlsanity.com/paper/2410.03315/) (2024)
- [Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting](https://mlsanity.com/paper/2302.05049/) (2023)
- [Towards Efficient Task-Driven Model Reprogramming with Foundation Models](https://mlsanity.com/paper/2304.02263/) (2023)
- [UFDA: Universal Federated Domain Adaptation with Practical Assumptions](https://mlsanity.com/paper/2311.15570/) (2023)
- [Lighter, Better, Faster Multi-Source Domain Adaptation with Gaussian Mixture Models and Optimal Transport](https://mlsanity.com/paper/2404.10261/) (2024)
- [Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2107.06707/) (2021)
- [Federated and Generalized Person Re-identification through Domain and Feature Hallucinating](https://mlsanity.com/paper/2203.02689/) (2022)
- [Gated Domain Units for Multi-source Domain Generalization](https://mlsanity.com/paper/2206.12444/) (2022)
- [CoSDA: Continual Source-Free Domain Adaptation](https://mlsanity.com/paper/2304.06627/) (2023)
- [Post-Deployment Adaptation with Access to Source Data via Federated Learning and Source-Target Remote Gradient Alignment](https://mlsanity.com/paper/2308.16735/) (2023)
- [Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2309.07670/) (2023)
- [Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Model](https://mlsanity.com/paper/2402.13122/) (2024)
- [Federated Domain Generalization with Domain-specific Soft Prompts Generation](https://mlsanity.com/paper/2509.20807/) (2025)
- [Domain Generalization for Prostate Segmentation in Transrectal Ultrasound Images: A Multi-center Study](https://mlsanity.com/paper/2209.02126/) (2022)

## Abstract (arXiv)

Conventional unsupervised multi-source domain adaptation (UMDA) methods assume all source domains can be accessed directly. This neglects the privacy-preserving policy, that is, all the data and computations must be kept decentralized. There exists three problems in this scenario: (1) Minimizing the domain distance requires the pairwise calculation of the data from source and target domains, which is not accessible. (2) The communication cost and privacy security limit the application of UMDA methods (e.g., the domain adversarial training). (3) Since users have no authority to check the data quality, the irrelevant or malicious source domains are more likely to appear, which causes negative transfer. In this study, we propose a privacy-preserving UMDA paradigm named Knowledge Distillation based Decentralized Domain Adaptation (KD3A), which performs domain adaptation through the knowledge distillation on models from different source domains. KD3A solves the above problems with three components: (1) A multi-source knowledge distillation method named Knowledge Vote to learn high-quality domain consensus knowledge. (2) A dynamic weighting strategy named Consensus Focus to identify both the malicious and irrelevant domains. (3) A decentralized optimization strategy for domain distance named BatchNorm MMD. The extensive experiments on DomainNet demonstrate that KD3A is robust to the negative transfer and brings a 100x reduction of communication cost compared with other decentralized UMDA methods. Moreover, our KD3A significantly outperforms state-of-the-art UMDA approaches.