Smart Information Exchange for Unsupervised Federated Learning via Reinforcement Learning (2402.09629v1)
Abstract: One of the main challenges of decentralized machine learning paradigms such as Federated Learning (FL) is the presence of local non-i.i.d. datasets. Device-to-device transfers (D2D) between distributed devices has been shown to be an effective tool for dealing with this problem and robust to stragglers. In an unsupervised case, however, it is not obvious how data exchanges should take place due to the absence of labels. In this paper, we propose an approach to create an optimal graph for data transfer using Reinforcement Learning. The goal is to form links that will provide the most benefit considering the environment's constraints and improve convergence speed in an unsupervised FL environment. Numerical analysis shows the advantages in terms of convergence speed and straggler resilience of the proposed method to different available FL schemes and benchmark datasets.
- H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. Aguera y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Proc. 20th Intl. Conf. Artif. Intell. and Stat. (AISTATS), 2017, pp. 1273–1282.
- S. Hosseinalipour, C. G. Brinton, V. Aggarwal, H. Dai and M. Chiang, “From Federated to Fog Learning: Distributed Machine Learning over Heterogeneous Wireless Networks,” in IEEE Commun. Mag., vol. 58, no. 12, pp. 41-47, 2020.
- S. Shen, Y. Han, X. Wang, and Y. Wang, “Computation Offloading with Multiple Agents in Edge-Computing–Supported IoT,” in ACM Trans. Sen. Netw., vol. 16, no. 8, pp. 1-27, 2019.
- S. Wang, M. Lee, S. Hosseinalipour, R. Morabito, M. Chiang, and C. G. Brinton, “Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation,” in Proc. IEEE Conf. Comput. Commun. (INFOCOM), 2021, pp. 1-10.
- D. Alistarh, D. Grubic, J. Li, R. Tomioka, and M. Vojnovic, “QSGD: Communication-efficient SGD via gradient quantization and encoding,” in Proc. Adv. Neural Inf. Process. Syst., 2017, pp. 1709–1720.
- W Wen, C Xu, F Yan, C Wu, Y Wang, Y Chen and H Li, “TernGrad: Ternary gradients to reduce communication in distributed deep learning,” in proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2017, pp. 1–11.
- S. Wagle, A. B. Das, D. J. Love, C. G. Brinton, “A Reinforcement Learning-Based Approach to Graph Discovery in D2D-Enabled Federated Learning,” in proc. IEEE Global Commun. Conf. (GLOBECOM), 2023.
- S. Wagle, S. Hosseinalipour, N. Khosravan, M. Chiang and C. G. Brinton, “Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange,” in Proc. IEEE Global Commun. Conf. (GLOBECOM), 2022, pp. 492-497.
- S. Rai, J. S. Bhatt and S. K. Patra “An unsupervised deep learning framework for medical image denoising,” preprint [available online], arXiv: 2103.06575, 2021.
- Z. Chen, C. K. Yeo, B. S. Lee and C. T. Lau, “Autoencoder-based network anomaly detection,” in Proc. Wirel. Telecomm. Symp. (WTS), 2018, pp. 1-5.
- T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V. Smith, “Federated optimization in heterogeneous networks,” in proc. Conf. Mach. Learn. and Sys., 2020.
- H. Xiao, K. Rasul, and R. Vollgraf, “Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,” preprint [available online], arXiv:1708.07747, 2017.
- T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A simple framework for contrastive learning of visual representations,” in Proc. Int. Conf. Mach. Learn. (ICML), 2020, pp. 1597–1607.
- K. Hsieh, A. Phanishayee, O. Mutlu, and P. B. Gibbons, “The non-iid data quagmire of decentralized machine learning,” in Proc. Intl. Conf. on Mach. Learn. (ICML), 2020, pp. 4387-4398.
- K. Pearson, “On lines and planes of closest fit to systems of points in space,” Philosophical Magazine, vol. 2, no. 6, pp. 559–572, 1901.
- D. Arthur and S. Vassilvitskii, “K-means++: The advantages of careful seeding,” in proc. Ann. ACM-SIAM Symp. Disc. Alg., 2007, pp. 1027-1035.
- A. Krizhevsky and G. Hinton, “Learning multiple layers of features from tiny images,” Master’s thesis, Univ. Tront, 2009.
- P. Bholowalia and A. Kumar, “EBK-means: A clustering technique based on elbow method and k-means in WSN,” Intl. Jour. Comp. Applications, vol. 105, no. 9, 2014.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.