Abstract
Federated domain adaptation system aims to address the problem of domain shift in a federated learning (FL) framework, where knowledge learned from distributed source domains can be readily transferred to the target domain. However, federated domain adaptation suffers from two challenges: (1) Inefficient assignment of source domain weights. (2) The joint distributions of feature and category across domains are poorly aligned. To solve the above problems, we propose a novel unsupervised federated domain adaptation (UFDA) approach called Federated Multi-Discriminative Adversarial Domain Adaptation (FMDADA). Firstly, we propose a FL aggregation scheme (F-DIS), which assigns weights to distributed source domains with different contribution rates based on a measure of cross-domain discrepancy. Secondly, we facilitate the joint distribution alignment of feature and category by designing multiple tightly coupled joint classifiers, which facilitates the positive transfer of source domain knowledge. Finally, extensive experimental results on three datasets demonstrate the effectiveness of FMDADA for UFDA problem. Compared to the currently advanced comparison approaches, the accuracy of FMDADA is significantly improved, reaching 54.7% and achieving an improvement of 5.9% on the large-scale dataset DomainNet.
Similar content being viewed by others
Availability of data and materials
All data is publicly available.
Code availability
Contact the authors for access to the code.
References
McMahan B, Moore E, Ramage D, Hampson S, Arcas BA (2017) Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the artificial intelligence and statistics, pp 1273–1282
Yurochkin M, Agarwal M, Ghosh S, Greenewald K, Hoang N, Khazaeni Y (2019) Bayesian nonparametric federated learning of neural networks. In: Proceedings of the international conference on machine learning, pp 7252–7261
Park J, Han D-J, Choi M, Moon J (2021) Sageflow: robust federated learning against both stragglers and adversaries. Proc Adv Neural Inf Process Syst 34:840–851
Quinonero-Candela J, Sugiyama M, Schwaighofer A, Lawrence ND (2008) Dataset shift in machine learning, pp 1–299
Liang X, Lin Y, Fu H, Zhu L, Li X (2022) Rscfed: random sampling consensus federated semi-supervised learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10154–10163
Yu T, Bagdasaryan E, Shmatikov V (2020) Salvaging federated learning by local adaptation. Preprint at ar**v:2002.04758
Liu Y, Kang Y, **ng C, Chen T, Yang Q (2020) A secure federated transfer learning framework. IEEE Intell Syst 35:70–82
Li T, Sahu AK, Zaheer M, Sanjabi M, Talwalkar A, Smith V (2020) Federated optimization in heterogeneous networks. Proc Mach Learn Syst 2:429–450
Huang Y, Chu L, Zhou Z, Wang L, Liu J, Pei J, Zhang Y (2021) Personalized cross-silo federated learning on non-iid data. In: Proceedings of the AAAI conference on artificial intelligence, pp 7865–7873
Dinh TC, Tran N, Nguyen J (2020) Personalized federated learning with moreau envelopes. Proc Adv Neural Inf Process Syst 21394–21405
Gao L, Fu H, Li L, Chen Y, Xu M, Xu C-Z (2022) Feddc: Federated learning with non-iid data via local drift decoupling and correction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10112–10121
HassanPour Zonoozi M, Seydi V (2023) A survey on adversarial domain adaptation. Neural Process Lett 55:2429–2469
Westfechtel T, Yeh H-W, Zhang D, Harada T (2024) Gradual source domain expansion for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 1946–1955
Lee J, Jung D, Yim J, Yoon S (2022) Confidence score for source-free unsupervised domain adaptation. In: International conference on machine learning, pp 12365–12377
Peng X, Huang Z, Zhu Y, Saenko K (2020) Federated adversarial domain adaptation. Proceedings of the international conference on learning representations, 1–19
Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW (2010) A theory of learning from different domains. Mach Learn 79:151–175
Ben-David S, Blitzer J, Crammer K, Pereira F (2006) Analysis of representations for domain adaptation. Proceedings of the Advances in neural information processing systems, 137–144
Xu M, Zhang J, Ni B, Li T, Wang C, Tian Q, Zhang W (2020) Adversarial domain adaptation with domain mixup. In: Proceedings of the AAAI conference on artificial intelligence, pp 6502–6509
Pei Z, Cao Z, Long M, Wang J (2018) Multi-adversarial domain adaptation. In: Proceedings of the Thirty-second AAAI conference on artificial intelligence, pp 3934–3941
Tang H, Jia K (2020) Discriminative adversarial domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, pp 5940–5947
Yeganeh Y, Farshad A, Navab N, Albarqouni S (2020) Inverse distance aggregation for federated learning with non-iid data. In: Domain adaptation and representation transfer, and distributed and collaborative learning, pp 150–159
Li X, Jiang M, Zhang X, Kamp M, Dou Q (2021) Fedbn: Federated learning on non-iid features via local batch normalization, 1–12
Ge P, Ren C-X, Xu X-L, Yan H (2023) Unsupervised domain adaptation via deep conditional adaptation network. Pattern Recognit 134:4488–4503
Wei G, Lan C, Zeng W, Chen Z (2021) Metaalign: Coordinating domain alignment and classification for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 16643–16653
Du Z, Li J, Su H, Zhu L, Lu K (2021) Cross-domain gradient discrepancy minimization for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 3937–3946
Mei Z, Ye P, Ye H, Li B, Guo J, Chen T, Ouyang W (2023) Automatic loss function search for adversarial unsupervised domain adaptation. IEEE Trans Circ Syst Video Tech 33:5868–5881
Akkaya IB, Altinel F, Halici U (2021) Self-training guided adversarial domain adaptation for thermal imagery. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4322–4331
Gao Z, Zhang S, Huang K, Wang Q, Zhong C (2021) Gradient distribution alignment certificates better adversarial domain adaptation. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 8937–8946
Long M, Cao Z, Wang J, Jordan MI (2018) Conditional adversarial domain adaptation. Proceedings of the Advances in neural information processing systems, 1647–1657
Cheng Z, Wang S, Yang D, Qi J, **ao M, Yan C (2024) Deep joint semantic adaptation network for multi-source unsupervised domain adaptation. Pattern Recognit 151:1–11
Park GY, Lee SW (2021) Information-theoretic regularization for multi-source domain adaptation. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 9214–9223
Zhao S, Wang G, Zhang S, Gu Y, Li Y, Song Z, Xu P, Hu R, Chai H, Keutzer K (2020) Multi-source distilling domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, pp 12975–12983
Yan H, Ding Y, Li P, Wang Q, Xu Y, Zuo W (2017) Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2272–2281
Peng X, Bai Q, **a X, Huang Z, Saenko K, Wang B (2019) Moment matching for multi-source domain adaptation. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 1406–1415
Zhao H, Zhang S, Wu G, Gordon GJ et al (2018) Multiple source domain adaptation with adversarial learning. Proceedings of the 2018 international conference on learning representations, 1–24
Feng H, You Z, Chen M, Zhang T, Zhu M, Wu F, Wu C, Chen W (2021) Kd3a: Unsupervised multi-source decentralized domain adaptation via knowledge distillation. In: Proceedings of the international conference on machine learning, pp 3274–3283
Gong B, Shi Y, Sha F, Grauman K (2012) Geodesic flow kernel for unsupervised domain adaptation. In: Proceedings of the 2012 IEEE conference on computer vision and pattern recognition, pp 2066–2073
Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: Proceedings of the international conference on machine learning, pp 1180–1189
Yang L, Balaji Y, Lim S-N, Shrivastava A (2020) Curriculum manager for source selection in multi-source domain adaptation. In: Proceedings of the european conference on computer vision, pp 608–624
Liu Y-H, Ren C-X (2022) A two-way alignment approach for unsupervised multi-source domain adaptation. Pattern Recognit 124:1–13
Liang J, Hu D, Feng J (2020) Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In: International conference on machine learning, pp 6028–6039
Wang B, Li G, Wu C, Zhang W, Zhou J, Wei Y (2022) A framework for self-supervised federated domain adaptation. EURASIP J Wirel Commun Netw 2022:1–17
Wei Y, Han Y (2023) Exploring instance relation for decentralized multi-source domain adaptation. In: Proceedings of the IEEE International conference on acoustics, speech and signal processing, pp 5031–5040
Zhang Y, Tang H, Jia K, Tan M (2019) Domain-symmetric networks for adversarial domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5031–5040
Cui S, Wang S, Zhuo J, Su C, Huang Q, Tian Q (2020) Gradually vanishing bridge for adversarial domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12455–12464
Li S, **e M, Lv F, Liu CH, Liang J, Qin C, Li W (2021) Semantic concentration for domain adaptation. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 9102–9111
Wang R, Wu Z, Weng Z, Chen J, Qi G-J, Jiang Y-G (2022) Cross-domain contrastive learning for unsupervised domain adaptation. IEEE Trans Multimedia, 1–10. https://doi.org/10.1109/TMM.2022.3146744
Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: Proceedings of the european conference on computer vision, pp 213–226
Acknowledgements
This research is supported by the National Natural Science Foundation of China (NSFC) under grant number 62172377, the Taishan Scholars Program of Shandong province under grant numbers tsqn202312102, and the Startup Research Foundation for Distinguished Scholars under grant number 202112016.
Author information
Authors and Affiliations
Contributions
All authors contributed to writing and research.
Corresponding author
Ethics declarations
Conflict of interest
There is no conflict of interest.
Ethics approval
Not Applicable.
Consent to participate
Not Applicable.
Consent for publication
Not Applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chi, H., **a, H., Xu, S. et al. FMDADA: Federated multi-discriminative adversarial domain adaptation. Appl Intell (2024). https://doi.org/10.1007/s10489-024-05592-x
Accepted:
Published:
DOI: https://doi.org/10.1007/s10489-024-05592-x