Abstract
Federated Learning (FL) aims to train machine learning models by decentralized data without direct data sharing. Nevertheless, the heterogeneity of data across FL participants has significantly prevented federated models from competitive performance. In this paper, we consider this issue as the consequence of knowledge forgetting, since the local update process in FL may result in catastrophic forgetting of the knowledge learned from other participants. Motivated by the recent advance in incremental learning techniques, we address this issue by overcoming the sever knowledge forgetting caused by data isolation. We propose a novel method called FedKL (Federated Learning with Knowledge Lock), in which knowledge distillation techniques are employed to maintain the previously learned knowledge. Our extensive experiment results demonstrate that FedKL achieves superior performance than prior methods, with over 3.4% and 3.5% accuracy improvements on CIFAR-10 and CIFAR-100 respectively, compared with the popular FL algorithm FedAvg. Furthermore, we also explore the benefits of introducing shared exemplars (a fraction of local data) to FedKL. In the experiments, we select and share 10 samples per class for FedKL and the baseline methods. As a result, FedKL obtains 2.56% accuracy increase on CIFAR-10, instead of the marginal improvements on prior methods (less than 1.5%
Supported by the Science and Technology Innovation 2030-Key Project under Grant 2021ZD0201404.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
\(\text {Sigmoid}(x)=1/(1+e^{-x})\).
- 2.
- 3.
\(\varTheta \) denotes the parameters of the model and \(\varTheta ^t\) denotes the parameters at the t-th round.
References
Arivazhagan, M.G., Aggarwal, V., Singh, A.K., Choudhary, S.: Federated learning with personalization layers. arXiv preprint arXiv:1912.00818 (2019)
Duan, M., et al.: Astraea: self-balancing federated learning for improving classification accuracy of mobile deep learning applications. In: 2019 IEEE 37th International Conference on Computer Design (ICCD), pp. 246–254. IEEE (2019)
Fallah, A., Mokhtari, A., Ozdaglar, A.: Personalized federated learning with theoretical guarantees: a model-agnostic meta-learning approach. Adv. Neural Inf. Process. Syst. 33, 3557–3568 (2020)
Ghosh, A., Chung, J., Yin, D., Ramchandran, K.: An efficient framework for clustered federated learning. Adv. Neural Inf. Process. Syst. 33, 19586–19597 (2020)
Ghosh, A., Hong, J., Yin, D., Ramchandran, K.: Robust federated learning in a heterogeneous environment. arXiv preprint arXiv:1906.06629 (2019)
Hanzely, F., Richtárik, P.: Federated learning of a mixture of global and local models. arXiv preprint arXiv:2002.05516 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Huang, Y., et al.: Personalized cross-silo federated learning on Non-IID data (2021)
Ji, S., Pan, S., Long, G., Li, X., Jiang, J., Huang, Z.: Learning private neural language modeling with attentive aggregation. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2019)
Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S., Stich, S., Suresh, A.T.: Scaffold: stochastic controlled averaging for federated learning. In: International Conference on Machine Learning, pp. 5132–5143. PMLR (2020)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)
Kopparapu, K., Lin, E.: FedFMC: sequential efficient federated learning on non-iid data. arXiv preprint arXiv:2006.10937 (2020)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. arXiv preprint arXiv:1812.06127 (2018)
Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935–2947 (2017)
Liang, P.P., et al.: Think locally, act globally: Federated learning with local and global representations. arXiv preprint arXiv:2001.01523 (2020)
Lin, T., Kong, L., Stich, S.U., Jaggi, M.: Ensemble distillation for robust model fusion in federated learning. arXiv preprint arXiv:2006.07242 (2020)
Liu, Y., Kang, Y., Xing, C., Chen, T., Yang, Q.: A secure federated transfer learning framework. IEEE Intell. Syst. 35(4), 70–82 (2020)
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282. PMLR (2017)
Peng, X., Huang, Z., Zhu, Y., Saenko, K.: Federated adversarial domain adaptation. In: International Conference on Learning Representations (2019)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: ICaRL: incremental classifier and representation learning. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 2001–2010 (2017)
Reddi, S.J., et al.: Adaptive federated optimization. In: International Conference on Learning Representations (2020)
Sattler, F., Müller, K.R., Samek, W.: Clustered federated learning: model-agnostic distributed multitask optimization under privacy constraints. IEEE Trans. Neural Networks Learn. Syst. 39, 3710–3722 (2020)
Shin, M., Hwang, C., Kim, J., Park, J., Bennis, M., Kim, S.L.: XOR mixup: privacy-preserving data augmentation for one-shot federated learning. arXiv preprint arXiv:2006.05148 (2020)
Shoham, N., et al.: Overcoming forgetting in federated learning on Non-IID data. arXiv preprint arXiv:1910.07796 (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Smith, V., Chiang, C.K., Sanjabi, M., Talwalkar, A.: Federated multi-task learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 4427–4437 (2017)
Tuor, T., Wang, S., Ko, B.J., Liu, C., Leung, K.K.: Overcoming noisy and irrelevant data in federated learning. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 5020–5027. IEEE (2021)
Wang, S., et al.: Adaptive federated learning in resource constrained edge computing systems. IEEE J. Sel. Areas Commun. 37(6), 1205–1221 (2019)
Yang, Q., Liu, Y., Cheng, Y., Kang, Y., Chen, T., Yu, H.: Federated learning. Synth. Lect. Artif. Intell. Mach. Learn. 13(3), 1–207 (2019)
Yoon, J., Jeong, W., Lee, G., Yang, E., Hwang, S.J.: Federated continual learning with weighted inter-client transfer. In: International Conference on Machine Learning, pp. 12073–12086. PMLR (2021)
Yoshida, N., Nishio, T., Morikura, M., Yamamoto, K., Yonetani, R.: Hybrid-FL: cooperative learning mechanism using Non-IID data in wireless networks. arXiv preprint arXiv:1905.07210 (2019)
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., Chandra, V.: Federated learning with Non-IID data. arXiv preprint arXiv:1806.00582 (2018)
Zhu, H., Xu, J., Liu, S., Jin, Y.: Federated learning on Non-IID data: a survey. arXiv preprint arXiv:2106.06843 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wei, G., Li, X. (2022). Knowledge Lock: Overcoming Catastrophic Forgetting in Federated Learning. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13280. Springer, Cham. https://doi.org/10.1007/978-3-031-05933-9_47
Download citation
DOI: https://doi.org/10.1007/978-3-031-05933-9_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05932-2
Online ISBN: 978-3-031-05933-9
eBook Packages: Computer ScienceComputer Science (R0)