Abstract
In the federated learning paradigm, multiple mobile clients train their local models independently based on the datasets generated by edge devices, and the server aggregates the model parameters received from multiple clients to form a global model. Conventional methods aggregate gradient parameters and statistical parameters without distinction, which leads to large aggregation bias due to cross-model distribution covariate shift (CDCS), and results in severe performance drop for federated learning under non-IID data. In this paper, we propose a novel decoupled parameter aggregation method called FedDNA to deal with the performance issues caused by CDCS. With the proposed method, the gradient parameters are aggregated using the conventional federated averaging method, and the statistical parameters are aggregated with an importance weighting method to reduce the divergence between the local models and the central model to optimize collaboratively by an adversarial learning algorithm based on variational autoencoder (VAE). Extensive experiments based on various federated learning scenarios with four open datasets show that FedDNA achieves significant performance improvement compared to the state-of-the-art methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The source code will be publicly available after acceptance.
References
Acar, D.A.E., Zhao, Y., Matas, R., Mattina, M., Whatmough, P., Saligrama, V.: Federated learning based on dynamic regularization. In: Proceedings of ICLR (2021)
Chen, T., Giannakis, G., Sun, T., Yin, W.: Lag: lazily aggregated gradient for communication-efficient distributed learning. In: Proceedings of NIPS, pp. 5050–5060 (2018)
Go, A., Bhayani, R., Huang, L.: Twitter sentiment classification using distant supervision (2009). http://help.sentiment140.com/home
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, pp. 770–778 (2016)
Hsieh, K., Phanishayee, A., Mutlu, O., Gibbons, P.B.: The Non-IID data quagmire of decentralized machine learning. In: Proceedings of ICML (2020)
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of CVPR, pp. 2261–2269 (2017)
Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging (2015). http://arxiv.org/abs/1508.01991
Ji, J., Chen, X., Wang, Q., Yu, L., Li, P.: Learning to learn gradient aggregation by gradient descent. In: Proceedings of IJCAI, pp. 2614–2620 (2019)
Jiang, L., Tan, R., Lou, X., Lin, G.: On lightweight privacy-preserving collaborative learning for internet-of-things objects. In: Proceedings of IoTDI, pp. 70–81 (2019)
Joyce, J.M.: Kullback-Leibler Divergence, pp. 720–722 (2011)
Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S., Stich, S., Suresh, A.T.: SCAFFOLD: stochastic controlled averaging for federated learning. In: Proceedings of ICML (2020)
Killeen, P.R.: An alternative to null-hypothesis significance tests. Psychol. Sci. 16(5), 345–53 (2005)
Kingma, D., Welling, M.: Auto-encoding variational bayes. In: Proceedings of ICLR (2014)
Konecny, J., McMahan, H.B., Ramage, D.: Federated optimization: Distributed optimization beyond the datacenter. In: NIPS Optimization for Machine Learning Workshop 2015, p. 5 (2015)
Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report (2009)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, pp. 2278–2324 (1998)
LeCun, Y., Cortes, C., Burges, C.: MNIST handwritten digit database. ATT Labs (2010). http://yann.lecun.com/exdb/mnist
Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. In: Proceedings of MLSys, pp. 429–450 (2020)
Li, T., Sanjabi, M., Smith, V.: Fair resource allocation in federated learning. In: Proceedings of ICLR (2020)
Li, X., Jiang, M., Zhang, X., Kamp, M., Dou, Q.: FedBN: federated learning on Non-IID features via local batch normalization. In: Proceedings of ICLR (2021)
Malinovsky, G., Kovalev, D., Gasanov, E., Condat, L., Richtarik, P.: From local SGD to local fixed-point methods for federated learning. In: Proceedings of ICML (2020)
McMahan, B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Proceedings of AISTATS, vol. 54, pp. 1273–1282 (2017)
Mohri, M., Sivek, G., Suresh, A.T.: Agnostic federated learning. In: ICML (2019)
Pathak, R., Wainwright, M.J.: FedSplit: an algorithmic framework for fast federated optimization. In: Proceedings of NeurIPS, vol. 33 (2020)
Reisizadeh, A., Farnia, F., Pedarsani, R., Jadbabaie, A.: Robust federated learning: the case of affine distribution shifts. In: Proceedings of NeurIPS (2020)
Rothchild, D., et al.: FetchSGD: communication-efficient federated learning with sketching. In: Proceedings of ICML (2020)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.: MobilenetV2: inverted residuals and linear bottlenecks. In: Proceedings of CVPR, pp. 4510–4520 (2018)
Wang, H., Yurochkin, M., Sun, Y., Papailiopoulos, D., Khazaeni, Y.: Federated learning with matched averaging. In: Proceedings of ICLR (2020)
Wang, J., Liu, Q., Liang, H., Joshi, G., Poor, H.V.: Tackling the objective inconsistency problem in heterogeneous federated optimization. In: Proceedings of NeurIPS (2020)
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms (2017)
Yu, F.X., Rawat, A.S., Menon, A., Kumar, S.: FedAwS: federated learning with only positive labels. In: Proceedings of ICML (2020)
Yuan, H., Ma, T.: Federated accelerated stochastic gradient descent. In: Proceedings of NeurIPS, vol. 33 (2020)
Yurochkin, M., Agarwal, M., Ghosh, S., Greenewald, K., Hoang, N., Khazaeni, Y.: Bayesian nonparametric federated learning of neural networks. In: Proceedings of ICML (2019)
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., Chandra, V.: Federated learning with Non-IID data. arXiv abs/1806.00582 (2018)
Zhu, H., Jin, Y.: Multi-objective evolutionary federated learning. IEEE Trans. Neural Netw. Learn. Syst. 31(4), 1310–1322 (2020)
Acknowledgment
This work was partially supported by the National Key R&D Program of China (Grant No. 2018YFB1004704), the National Natural Science Foundation of China (Grant Nos. 61972196, 61832008, 61832005), the Key R&D Program of Jiangsu Province, China (Grant No. BE2018116), the Collaborative Innovation Center of Novel Software Technology and Industrialization, and the Sino-German Institutes of Social Computing.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Duan, JH., Li, W., Lu, S. (2021). FedDNA: Federated Learning with Decoupled Normalization-Layer Aggregation for Non-IID Data. In: Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2021. Lecture Notes in Computer Science(), vol 12975. Springer, Cham. https://doi.org/10.1007/978-3-030-86486-6_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-86486-6_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86485-9
Online ISBN: 978-3-030-86486-6
eBook Packages: Computer ScienceComputer Science (R0)